Go Back
Choose this branch
Choose this branch
meritocratic
regular
democratic
hot
top
alive
14 posts
Threat Models
Sharp Left Turn
18 posts
Coordination / Cooperation
Fiction
Site Meta
AI Risk Concrete Stories
AMA
Multipolar Scenarios
Prisoner's Dilemma
Paperclip Maximizer
Moloch
Q&A (format)
222
What failure looks like
paulfchristiano
3y
49
214
A central AI alignment problem: capabilities generalization, and the sharp left turn
So8res
6mo
48
180
Another (outer) alignment failure story
paulfchristiano
1y
38
109
Less Realistic Tales of Doom
Mark Xu
1y
13
87
Rogue AGI Embodies Valuable Intellectual Property
Mark Xu
1y
9
59
Refining the Sharp Left Turn threat model, part 1: claims and mechanisms
Vika
4mo
3
58
Vignettes Workshop (AI Impacts)
Daniel Kokotajlo
1y
3
51
Survey on AI existential risk scenarios
Sam Clarke
1y
11
43
Distinguishing AI takeover scenarios
Sam Clarke
1y
11
42
Refining the Sharp Left Turn threat model, part 2: applying alignment techniques
Vika
25d
4
38
AI Neorealism: a threat model & success criterion for existential safety
davidad
5d
0
33
We may be able to see sharp left turns coming
Ethan Perez
3mo
26
28
AI X-risk >35% mostly based on a recent peer-reviewed argument
michaelcohen
1mo
31
26
Investigating AI Takeover Scenarios
Sammy Martin
1y
1
255
It Looks Like You're Trying To Take Over The World
gwern
9mo
125
154
What Multipolar Failure Looks Like, and Robust Agent-Agnostic Processes (RAAPs)
Andrew_Critch
1y
60
132
AI coordination needs clear wins
evhub
3mo
15
121
The next decades might be wild
Marius Hobbhahn
5d
21
118
Late 2021 MIRI Conversations: AMA / Discussion
Rob Bensinger
9mo
208
116
Prisoners' Dilemma with Costs to Modeling
Scott Garrabrant
4y
20
115
Welcome & FAQ!
Ruby
1y
8
91
Introducing the AI Alignment Forum (FAQ)
habryka
4y
8
76
What Failure Looks Like: Distilling the Discussion
Ben Pace
2y
14
76
Announcing AlignmentForum.org Beta
Raemon
4y
35
65
We're Redwood Research, we do applied alignment research, AMA
Nate Thomas
1y
3
64
AI takeoff story: a continuation of progress by other means
Edouard Harris
1y
13
48
Clarifying “What failure looks like”
Sam Clarke
2y
14
42
My Overview of the AI Alignment Landscape: Threat Models
Neel Nanda
12mo
4