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)
155
The next decades might be wild
Marius Hobbhahn
5d
21
36
AI X-risk >35% mostly based on a recent peer-reviewed argument
michaelcohen
1mo
31
50
We may be able to see sharp left turns coming
Ethan Perez
3mo
26
36
Refining the Sharp Left Turn threat model, part 2: applying alignment techniques
Vika
25d
4
253
A central AI alignment problem: capabilities generalization, and the sharp left turn
So8res
6mo
48
134
AI coordination needs clear wins
evhub
3mo
15
71
Refining the Sharp Left Turn threat model, part 1: claims and mechanisms
Vika
4mo
3
109
Welcome & FAQ!
Ruby
1y
8
119
Late 2021 MIRI Conversations: AMA / Discussion
Rob Bensinger
9mo
208
50
My Overview of the AI Alignment Landscape: Threat Models
Neel Nanda
12mo
4
79
What Failure Looks Like: Distilling the Discussion
Ben Pace
2y
14
210
Another (outer) alignment failure story
paulfchristiano
1y
38
70
Rogue AGI Embodies Valuable Intellectual Property
Mark Xu
1y
9
86
Introducing the AI Alignment Forum (FAQ)
habryka
4y
8
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
118
An Update on Academia vs. Industry (one year into my faculty job)
David Scott Krueger (formerly: capybaralet)
3mo
18
35
The Dumbest Possible Gets There First
Artaxerxes
4mo
7
18
Concrete Advice for Forming Inside Views on AI Safety
Neel Nanda
4mo
6
43
A survey of tool use and workflows in alignment research
Logan Riggs
9mo
5
19
Some ideas for epistles to the AI ethicists
Charlie Steiner
3mo
0
43
What technologies could cause world GDP doubling times to be <8 years?
Daniel Kokotajlo
2y
44
35
New paper: Corrigibility with Utility Preservation
Koen.Holtman
3y
11
56
AI x-risk reduction: why I chose academia over industry
David Scott Krueger (formerly: capybaralet)
1y
14
40
[Linkpost] Existential Risk Analysis in Empirical Research Papers
Dan H
5mo
0
21
Reading the ethicists 2: Hunting for AI alignment papers
Charlie Steiner
6mo
1
23
Techniques for optimizing worst-case performance
paulfchristiano
3y
12