Go Back
Choose this branch
Choose this branch
meritocratic
regular
democratic
hot
top
alive
1209 posts
Logic & Mathematics
Probability & Statistics
Philosophy of Language
Abstraction
Physics
Philosophy
Bayes' Theorem
Epistemology
Rationality Quotes
Truth, Semantics, & Meaning
Causality
Logical Induction
2540 posts
Rationality
Relationships (Interpersonal)
Heuristics & Biases
Exercises / Problem-Sets
Communication Cultures
Conversation (topic)
Fiction (Topic)
Impact Regularization
Techniques
Virtues
Planning & Decision-Making
Disagreement
30
our deepest wishes
carado
23h
0
181
Finite Factored Sets in Pictures
Magdalena Wache
9d
29
11
Slick hyperfinite Ramsey theory proof
Alok Singh
1d
2
140
Logical induction for software engineers
Alex Flint
17d
2
58
Formalization as suspension of intuition
adamShimi
9d
18
24
Proof as mere strong evidence
adamShimi
6d
15
39
A dynamical systems primer for entropy and optimization
Alex_Altair
10d
3
259
Introduction to abstract entropy
Alex_Altair
2mo
70
5
Can we, in principle, know the measure of counterfactual quantum branches?
sisyphus
2d
15
55
AI takeover tabletop RPG: "The Treacherous Turn"
Daniel Kokotajlo
20d
3
8
Using Information Theory to tackle AI Alignment: A Practical Approach
Daniel Salami
3d
4
51
Why square errors?
Aprillion (Peter Hozák)
24d
10
15
Questions about AI that bother me
Eleni Angelou
9d
2
13
Meaningful things are those the universe possesses a semantics for
Abhimanyu Pallavi Sudhir
8d
14
65
Shard Theory in Nine Theses: a Distillation and Critical Appraisal
LawrenceC
1d
9
56
Results from a survey on tool use and workflows in alignment research
jacquesthibs
1d
2
40
Positive values seem more robust and lasting than prohibitions
TurnTrout
3d
9
97
Setting the Zero Point
Duncan_Sabien
11d
38
91
Geometric Rationality is Not VNM Rational
Scott Garrabrant
23d
19
8
Overconfidence bubbles
kaputmi
2d
0
91
The Geometric Expectation
Scott Garrabrant
27d
10
55
MrBeast's Squid Game Tricked Me
lsusr
17d
1
71
Always know where your abstractions break
lsusr
23d
6
48
Biases are engines of cognition
remember
20d
7
16
Log-odds are better than Probabilities
Robert_AIZI
8d
4
61
Against a General Factor of Doom
Jeffrey Heninger
27d
18
35
Research Principles for 6 Months of AI Alignment Studies
Shoshannah Tekofsky
18d
3
263
The shard theory of human values
Quintin Pope
3mo
57