Go Back
Choose this branch
Choose this branch
meritocratic
regular
democratic
hot
top
alive
32 posts
Threat Models
Coordination / Cooperation
Sharp Left Turn
Fiction
AI Risk Concrete Stories
Site Meta
AMA
Multipolar Scenarios
Prisoner's Dilemma
Moloch
Paperclip Maximizer
Q&A (format)
51 posts
World Optimization
Existential Risk
Practical
Academic Papers
Ethics & Morality
AI Safety Camp
Symbol Grounding
Security Mindset
Software Tools
Careers
Surveys
Updated Beliefs (examples of)
189
The next decades might be wild
Marius Hobbhahn
5d
21
40
AI Neorealism: a threat model & success criterion for existential safety
davidad
5d
0
517
It Looks Like You're Trying To Take Over The World
gwern
9mo
125
30
Refining the Sharp Left Turn threat model, part 2: applying alignment techniques
Vika
25d
4
292
A central AI alignment problem: capabilities generalization, and the sharp left turn
So8res
6mo
48
136
AI coordination needs clear wins
evhub
3mo
15
44
AI X-risk >35% mostly based on a recent peer-reviewed argument
michaelcohen
1mo
31
83
Refining the Sharp Left Turn threat model, part 1: claims and mechanisms
Vika
4mo
3
67
We may be able to see sharp left turns coming
Ethan Perez
3mo
26
120
Late 2021 MIRI Conversations: AMA / Discussion
Rob Bensinger
9mo
208
252
What Multipolar Failure Looks Like, and Robust Agent-Agnostic Processes (RAAPs)
Andrew_Critch
1y
60
240
Another (outer) alignment failure story
paulfchristiano
1y
38
416
What failure looks like
paulfchristiano
3y
49
103
Welcome & FAQ!
Ruby
1y
8
82
Thoughts on AGI organizations and capabilities work
Rob Bensinger
13d
17
69
Deconfusing Direct vs Amortised Optimization
beren
18d
6
144
An Update on Academia vs. Industry (one year into my faculty job)
David Scott Krueger (formerly: capybaralet)
3mo
18
48
Some advice on independent research
Marius Hobbhahn
1mo
4
284
Six Dimensions of Operational Adequacy in AGI Projects
Eliezer Yudkowsky
6mo
65
80
Don't leave your fingerprints on the future
So8res
2mo
32
94
Linkpost: Github Copilot productivity experiment
Daniel Kokotajlo
3mo
4
201
Reshaping the AI Industry
Thane Ruthenis
6mo
34
76
Nearcast-based "deployment problem" analysis
HoldenKarnofsky
3mo
2
413
How To Get Into Independent Research On Alignment/Agency
johnswentworth
1y
33
30
POWERplay: An open-source toolchain to study AI power-seeking
Edouard Harris
1mo
0
83
Moral strategies at different capability levels
Richard_Ngo
4mo
14
177
Morality is Scary
Wei_Dai
1y
125
45
The Dumbest Possible Gets There First
Artaxerxes
4mo
7