0 |
Strong Evidence is Common
Mark Xu
|
|
1 |
“PR” is corrosive; “reputation” is not.
AnnaSalamon
|
|
2 |
Your Cheerful Price
Eliezer Yudkowsky
|
|
3 |
ARC's first technical report: Eliciting Latent Knowledge
paulfchristiano
|
|
4 |
This Can't Go On
HoldenKarnofsky
|
|
5 |
Rationalism before the Sequences
Eric Raymond
|
|
6 |
Lies, Damn Lies, and Fabricated Options
Duncan_Sabien
|
|
7 |
Fun with +12 OOMs of Compute
Daniel Kokotajlo
|
|
8 |
What 2026 looks like
Daniel Kokotajlo
|
|
9 |
Ngo and Yudkowsky on alignment difficulty
Eliezer Yudkowsky
|
|
10 |
How To Write Quickly While Maintaining Epistemic Rigor
johnswentworth
|
|
11 |
Science in a High-Dimensional World
johnswentworth
|
|
12 |
How factories were made safe
jasoncrawford
|
|
13 |
Cryonics signup guide #1: Overview
mingyuan
|
|
14 |
Making Vaccine
johnswentworth
|
|
15 |
Taboo "Outside View"
Daniel Kokotajlo
|
|
16 |
All Possible Views About Humanity's Future Are Wild
HoldenKarnofsky
|
|
17 |
Another (outer) alignment failure story
paulfchristiano
|
|
18 |
Split and Commit
Duncan_Sabien
|
|
19 |
What Multipolar Failure Looks Like, and Robust Agent-Agnostic Processes (RAAPs)
Andrew_Critch
|
|
20 |
There’s no such thing as a tree (phylogenetically)
eukaryote
|
|
21 |
The Plan
johnswentworth
|
|
22 |
Trapped Priors As A Basic Problem Of Rationality
Scott Alexander
|
|
23 |
Finite Factored Sets
Scott Garrabrant
|
|
24 |
Selection Theorems: A Program For Understanding Agents
johnswentworth
|
|
25 |
Slack Has Positive Externalities For Groups
johnswentworth
|
|
26 |
My research methodology
paulfchristiano
|
|
27 |
The Rationalists of the 1950s (and before) also called themselves “Rationalists”
Owain_Evans
|
|
28 |
Ruling Out Everything Else
Duncan_Sabien
|
|
29 |
Leaky Delegation: You are not a Commodity
Darmani
|
|
30 |
Feature Selection
Zack_M_Davis
|
|
31 |
Cup-Stacking Skills (or, Reflexive Involuntary Mental Motions)
Duncan_Sabien
|
|
32 |
larger language models may disappoint you [or, an eternally unfinished draft]
nostalgebraist
|
|
33 |
Self-Integrity and the Drowning Child
Eliezer Yudkowsky
|
|
34 |
Comments on Carlsmith's “Is power-seeking AI an existential risk?”
So8res
|
|
35 |
Working With Monsters
johnswentworth
|
|
36 |
Simulacrum 3 As Stag-Hunt Strategy
johnswentworth
|
|
37 |
Elephant seal 2
KatjaGrace
|
|
38 |
EfficientZero: How It Works
1a3orn
|
|
39 |
Lars Doucet's Georgism series on Astral Codex Ten
Sune
|
|
40 |
Catching the Spark
LoganStrohl
|
|
41 |
Specializing in Problems We Don't Understand
johnswentworth
|
|
42 |
Shoulder Advisors 101
Duncan_Sabien
|
|
43 |
Notes from "Don't Shoot the Dog"
juliawise
|
|
44 |
Why has nuclear power been a flop?
jasoncrawford
|
|
45 |
Whole Brain Emulation: No Progress on C. elgans After 10 Years
niconiconi
|
|
46 |
Frame Control
Aella
|
|
47 |
Worst-case thinking in AI alignment
Buck
|
|
48 |
Yudkowsky and Christiano discuss "Takeoff Speeds"
Eliezer Yudkowsky
|
|
49 |
You are probably underestimating how good self-love can be
charlie.rs
|
|
50 |
Infra-Bayesian physicalism: a formal theory of naturalized induction
Vanessa Kosoy
|
|
51 |
Jean Monnet: The Guerilla Bureaucrat
Martin Sustrik
|
|
52 |
Seven Years of Spaced Repetition Software in the Classroom
tanagrabeast
|
|
53 |
Bets, Bonds, and Kindergarteners
jefftk
|
|
54 |
Coordination Schemes Are Capital Investments
Raemon
|
|
55 |
The Point of Trade
Eliezer Yudkowsky
|
|
56 |
Law of No Evidence
Zvi
|
|
57 |
Discussion with Eliezer Yudkowsky on AGI interventions
Rob Bensinger
|
|
58 |
Saving Time
Scott Garrabrant
|
|
59 |
Intentionally Making Close Friends
Neel Nanda
|
|
60 |
What Do GDP Growth Curves Really Mean?
johnswentworth
|
|
61 |
The case for aligning narrowly superhuman models
Ajeya Cotra
|
|
62 |
The bonds of family and community: Poverty and cruelty among Russian peasants in the late 19th century
jasoncrawford
|
|
63 |
The Death of Behavioral Economics
habryka
|
|
64 |
Why I Am Not in Charge
Zvi
|
|
65 |
Politics is way too meta
Rob Bensinger
|
|
66 |
Where do your eyes go?
alkjash
|
|
67 |
Highlights from The Autobiography of Andrew Carnegie
jasoncrawford
|
|
68 |
Lessons I've Learned from Self-Teaching
TurnTrout
|
|
69 |
Grokking the Intentional Stance
jbkjr
|
|
70 |
Agency in Conway’s Game of Life
Alex Flint
|
|
71 |
Reneging Prosocially
Duncan_Sabien
|
|
72 |
Experimentally evaluating whether honesty generalizes
paulfchristiano
|
|
73 |
Birds, Brains, Planes, and AI: Against Appeals to the Complexity/Mysteriousness/Efficiency of the Brain
Daniel Kokotajlo
|
|
74 |
Unnatural Categories Are Optimized for Deception
Zack_M_Davis
|
|
75 |
Can you control the past?
Joe Carlsmith
|
|
76 |
A Brief Introduction to Container Logistics
Vitor
|
|
77 |
Core Pathways of Aging
johnswentworth
|
|
78 |
Imitative Generalisation (AKA 'Learning the Prior')
Beth Barnes
|
|
79 |
[Book review] Gödel, Escher, Bach: an in-depth explainer
Sam Marks
|
|
80 |
Selection Has A Quality Ceiling
johnswentworth
|
|
81 |
Book Review: A Pattern Language by Christopher Alexander
lincolnquirk
|
|
82 |
Technological stagnation: Why I came around
jasoncrawford
|
|
83 |
I'm from a parallel Earth with much higher coordination: AMA
Ben Pace
|
|
84 |
Redwood Research’s current project
Buck
|
|
85 |
What will 2040 probably look like assuming no singularity?
Daniel Kokotajlo
|
|
86 |
Reward Is Not Enough
Steven Byrnes
|
|
87 |
Coordination Skills I Wish I Had For the Pandemic
Raemon
|
|
88 |
Dear Self; We Need To Talk About Social Media
Elizabeth
|
|
89 |
Testing The Natural Abstraction Hypothesis: Project Intro
johnswentworth
|
|
90 |
How To Get Into Independent Research On Alignment/Agency
johnswentworth
|
|
91 |
Exercise: Taboo "Should"
johnswentworth
|
|
92 |
Precognition
jasoncrawford
|
|
93 |
Biology-Inspired AGI Timelines: The Trick That Never Works
Eliezer Yudkowsky
|
|
94 |
Visible Thoughts Project and Bounty Announcement
So8res
|
|
95 |
Unwitting cult leaders
Kaj_Sotala
|
|
96 |
Zvi’s Thoughts on the Survival and Flourishing Fund (SFF)
Zvi
|
|
97 |
RadVac Commercial Antibody Test Results
johnswentworth
|
|
98 |
Curing insanity with malaria
Swimmer963
|
|
99 |
Ngo and Yudkowsky on AI capability gains
Eliezer Yudkowsky
|
|
100 |
Going Out With Dignity
Tomás B.
|
|
101 |
Social behavior curves, equilibria, and radicalism
Eric Neyman
|
|
102 |
The feeling of breaking an Overton window
AnnaSalamon
|
|
103 |
The Coordination Frontier: Sequence Intro
Raemon
|
|
104 |
The Telephone Theorem: Information At A Distance Is Mediated By Deterministic Constraints
johnswentworth
|
|
105 |
Fixing The Good Regulator Theorem
johnswentworth
|
|
106 |
Soares, Tallinn, and Yudkowsky discuss AGI cognition
So8res
|
|
107 |
Where did the 5 micron number come from? Nowhere good. [Wired.com]
Elizabeth
|
|
108 |
The Prototypical Negotiation Game
johnswentworth
|
|
109 |
Three enigmas at the heart of our reasoning
Alex Flint
|
|
110 |
Gravity Turn
alkjash
|
|
111 |
Secure homes for digital people
paulfchristiano
|
|
112 |
Killing the ants
Joe Carlsmith
|
|
113 |
Choice Writings of Dominic Cummings
Connor_Flexman
|
|
114 |
Shared Frames Are Capital Investments in Coordination
johnswentworth
|
|
115 |
How do we prepare for final crunch time?
Eli Tyre
|
|
116 |
AI Risk for Epistemic Minimalists
Alex Flint
|
|
117 |
Kelly *is* (just) about logarithmic utility
abramdemski
|
|
118 |
What's Stopping You?
Neel Nanda
|
|
119 |
Testing The Natural Abstraction Hypothesis: Project Update
johnswentworth
|
|
120 |
Building Blocks of Politics: An Overview of Selectorate Theory
Yoav Ravid
|
|
121 |
The Case for Radical Optimism about Interpretability
Quintin Pope
|
|
122 |
Coherence arguments imply a force for goal-directed behavior
KatjaGrace
|
|
123 |
The Most Important Century: Sequence Introduction
HoldenKarnofsky
|
|
124 |
Beware over-use of the agent model
Alex Flint
|
|
125 |
Almost everyone should be less afraid of lawsuits
alyssavance
|
|
126 |
Decoupling deliberation from competition
paulfchristiano
|
|
127 |
Why did we wait so long for the threshing machine?
jasoncrawford
|
|
128 |
The blue-minimising robot and model splintering
Stuart_Armstrong
|
|
129 |
Tales from Prediction Markets
ike
|
|
130 |
A non-magical explanation of Jeffrey Epstein
lc
|
|
131 |
A few thought on the inner ring
KatjaGrace
|
|
132 |
Deliberate Play
jsteinhardt
|
|
133 |
Automating Auditing: An ambitious concrete technical research proposal
evhub
|
|
134 |
Benchmarking an old chess engine on new hardware
hippke
|
|
135 |
Transcript: "You Should Read HPMOR"
TurnTrout
|
|
136 |
Concentration of Force
Duncan_Sabien
|
|
137 |
Against neutrality about creating happy lives
Joe Carlsmith
|
|
138 |
Rules for Epistemic Warfare?
Gentzel
|
|
139 |
Morality is Scary
Wei_Dai
|
|
140 |
Norm Innovation and Theory of Mind
Raemon
|
|
141 |
Scott Alexander's "Ivermectin: Much More Than You Wanted To Know"
Raemon
|
|
142 |
Bad names make you open the box
Adam Zerner
|
|
143 |
Review of "Fun with +12 OOMs of Compute"
adamShimi
|
|
144 |
Random facts can come back to bite you
tailcalled
|
|
145 |
Coase's "Nature of the Firm" on Polyamory
1a3orn
|
|
146 |
The Upper Limit of Value
Davidmanheim
|
|
147 |
Your Dog is Even Smarter Than You Think
StyleOfDog
|
|
148 |
Robin Hanson's Grabby Aliens model explained - part 1
Writer
|
|