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)
319
What failure looks like
paulfchristiano
3y
49
253
A central AI alignment problem: capabilities generalization, and the sharp left turn
So8res
6mo
48
210
Another (outer) alignment failure story
paulfchristiano
1y
38
110
Less Realistic Tales of Doom
Mark Xu
1y
13
71
Refining the Sharp Left Turn threat model, part 1: claims and mechanisms
Vika
4mo
3
70
Rogue AGI Embodies Valuable Intellectual Property
Mark Xu
1y
9
67
Distinguishing AI takeover scenarios
Sam Clarke
1y
11
60
Survey on AI existential risk scenarios
Sam Clarke
1y
11
50
We may be able to see sharp left turns coming
Ethan Perez
3mo
26
47
Vignettes Workshop (AI Impacts)
Daniel Kokotajlo
1y
3
39
AI Neorealism: a threat model & success criterion for existential safety
davidad
5d
0
36
AI X-risk >35% mostly based on a recent peer-reviewed argument
michaelcohen
1mo
31
36
Refining the Sharp Left Turn threat model, part 2: applying alignment techniques
Vika
25d
4
27
Investigating AI Takeover Scenarios
Sammy Martin
1y
1
386
It Looks Like You're Trying To Take Over The World
gwern
9mo
125
203
What Multipolar Failure Looks Like, and Robust Agent-Agnostic Processes (RAAPs)
Andrew_Critch
1y
60
155
The next decades might be wild
Marius Hobbhahn
5d
21
134
AI coordination needs clear wins
evhub
3mo
15
119
Late 2021 MIRI Conversations: AMA / Discussion
Rob Bensinger
9mo
208
116
Prisoners' Dilemma with Costs to Modeling
Scott Garrabrant
4y
20
109
Welcome & FAQ!
Ruby
1y
8
95
Clarifying “What failure looks like”
Sam Clarke
2y
14
86
Introducing the AI Alignment Forum (FAQ)
habryka
4y
8
79
What Failure Looks Like: Distilling the Discussion
Ben Pace
2y
14
75
AI takeoff story: a continuation of progress by other means
Edouard Harris
1y
13
67
Announcing AlignmentForum.org Beta
Raemon
4y
35
56
We're Redwood Research, we do applied alignment research, AMA
Nate Thomas
1y
3
50
My Overview of the AI Alignment Landscape: Threat Models
Neel Nanda
12mo
4