LESSWRONG
LW

Curated Posts

Archive Recommendations

1924

Spotlight Items

Harry Potter and The Methods of Rationality

What if Harry was a scientist? What would you do if the universe had magic in it? 
A story that conveys many rationality concepts, helping to make them more visceral, intuitive and emotionally compelling.

Load More
271
Legible vs. Illegible AI Safety Problems
Ω
Wei Dai
1d
Ω
84
181
The Unreasonable Effectiveness of Fiction
Raelifin
5d
23
95
LLM-generated text is not testimony
TsviBT
8d
82
122
Cancer has a surprising amount of detail
Abhishaike Mahajan
12d
17
239
EU explained in 10 minutes
Martin Sustrik
15d
48
205
Do One New Thing A Day To Solve Your Problems
Algon
20d
28
182
The "Length" of "Horizons"
Adam Scholl
25d
27
293
Towards a Typology of Strange LLM Chains-of-Thought
1a3orn
1mo
28
155
What, if not agency?
Ω
abramdemski
1mo
Ω
27
56
Notes on fatalities from AI takeover
ryan_greenblatt
1mo
61
227
Ethical Design Patterns
AnnaSalamon
1mo
49
364
Four ways learning Econ makes people dumber re: future AI
Ω
Steven Byrnes
1mo
Ω
49
Load More
First Post: Chapter 1: A Day of Very Low Probability
494Welcome to LessWrong!
Ruby, Raemon, RobertM, habryka
6y
76
956AGI Ruin: A List of Lethalities
Ω
Eliezer Yudkowsky
3y
Ω
711
908Where I agree and disagree with Eliezer
Ω
paulfchristiano
3y
Ω
224
877Preface
Eliezer Yudkowsky
11y
17
876Eight Short Studies On Excuses
Scott Alexander
16y
254
794The Best Textbooks on Every Subject
lukeprog
15y
417
743The Company Man
Tomás B.
2mo
70
696The Rise of Parasitic AI
Adele Lopez
2mo
178
687SolidGoldMagikarp (plus, prompt generation)
Ω
Jessica Rumbelow, mwatkins
3y
Ω
208
682What an actually pessimistic containment strategy looks like
lc
4y
138