Go Back
Choose this branch
Choose this branch
meritocratic
regular
democratic
hot
top
alive
43 posts
World Optimization
Practical
AI Safety Camp
Ethics & Morality
Symbol Grounding
Security Mindset
Software Tools
Surveys
Careers
Updated Beliefs (examples of)
Organizational Culture & Design
Covid-19
8 posts
Existential Risk
Academic Papers
94
Thoughts on AGI organizations and capabilities work
Rob Bensinger
13d
17
48
Deconfusing Direct vs Amortised Optimization
beren
18d
6
93
Don't leave your fingerprints on the future
So8res
2mo
32
270
Six Dimensions of Operational Adequacy in AGI Projects
Eliezer Yudkowsky
6mo
65
41
Some advice on independent research
Marius Hobbhahn
1mo
4
118
An Update on Academia vs. Industry (one year into my faculty job)
David Scott Krueger (formerly: capybaralet)
3mo
18
78
Nearcast-based "deployment problem" analysis
HoldenKarnofsky
3mo
2
88
Linkpost: Github Copilot productivity experiment
Daniel Kokotajlo
3mo
4
314
How To Get Into Independent Research On Alignment/Agency
johnswentworth
1y
33
143
Reshaping the AI Industry
Thane Ruthenis
6mo
34
95
Moral strategies at different capability levels
Richard_Ngo
4mo
14
22
POWERplay: An open-source toolchain to study AI power-seeking
Edouard Harris
1mo
0
175
Morality is Scary
Wei_Dai
1y
125
30
New tool for exploring EA Forum, LessWrong and Alignment Forum - Tree of Tags
Filip Sondej
3mo
2
35
The Dumbest Possible Gets There First
Artaxerxes
4mo
7
40
[Linkpost] Existential Risk Analysis in Empirical Research Papers
Dan H
5mo
0
199
Some AI research areas and their relevance to existential safety
Andrew_Critch
2y
40
18
Concrete Advice for Forming Inside Views on AI Safety
Neel Nanda
4mo
6
41
A list of good heuristics that the case for AI x-risk fails
David Scott Krueger (formerly: capybaralet)
3y
14
35
New paper: Corrigibility with Utility Preservation
Koen.Holtman
3y
11
28
What I talk about when I talk about AI x-risk: 3 core claims I want machine learning researchers to address.
David Scott Krueger (formerly: capybaralet)
3y
13
23
Techniques for optimizing worst-case performance
paulfchristiano
3y
12