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
106
Thoughts on AGI organizations and capabilities work
Rob Bensinger
13d
17
27
Deconfusing Direct vs Amortised Optimization
beren
18d
6
106
Don't leave your fingerprints on the future
So8res
2mo
32
256
Six Dimensions of Operational Adequacy in AGI Projects
Eliezer Yudkowsky
6mo
65
34
Some advice on independent research
Marius Hobbhahn
1mo
4
80
Nearcast-based "deployment problem" analysis
HoldenKarnofsky
3mo
2
92
An Update on Academia vs. Industry (one year into my faculty job)
David Scott Krueger (formerly: capybaralet)
3mo
18
82
Linkpost: Github Copilot productivity experiment
Daniel Kokotajlo
3mo
4
107
Moral strategies at different capability levels
Richard_Ngo
4mo
14
215
How To Get Into Independent Research On Alignment/Agency
johnswentworth
1y
33
85
Reshaping the AI Industry
Thane Ruthenis
6mo
34
173
Morality is Scary
Wei_Dai
1y
125
34
New tool for exploring EA Forum, LessWrong and Alignment Forum - Tree of Tags
Filip Sondej
3mo
2
14
POWERplay: An open-source toolchain to study AI power-seeking
Edouard Harris
1mo
0
25
The Dumbest Possible Gets There First
Artaxerxes
4mo
7
191
Some AI research areas and their relevance to existential safety
Andrew_Critch
2y
40
26
[Linkpost] Existential Risk Analysis in Empirical Research Papers
Dan H
5mo
0
13
Concrete Advice for Forming Inside Views on AI Safety
Neel Nanda
4mo
6
46
A list of good heuristics that the case for AI x-risk fails
David Scott Krueger (formerly: capybaralet)
3y
14
39
New paper: Corrigibility with Utility Preservation
Koen.Holtman
3y
11
33
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
31
Techniques for optimizing worst-case performance
paulfchristiano
3y
12