Go Back
You can't go any further
You can't go any further
meritocratic
regular
democratic
hot
top
alive
15 posts
Threat Models
6 posts
Sharp Left Turn
437
What failure looks like
paulfchristiano
3y
49
266
What Multipolar Failure Looks Like, and Robust Agent-Agnostic Processes (RAAPs)
Andrew_Critch
1y
60
253
Another (outer) alignment failure story
paulfchristiano
1y
38
165
AI Could Defeat All Of Us Combined
HoldenKarnofsky
6mo
29
148
Clarifying AI X-risk
zac_kenton
1mo
23
116
Less Realistic Tales of Doom
Mark Xu
1y
13
97
Distinguishing AI takeover scenarios
Sam Clarke
1y
11
88
What Failure Looks Like: Distilling the Discussion
Ben Pace
2y
14
73
Survey on AI existential risk scenarios
Sam Clarke
1y
11
68
Threat Model Literature Review
zac_kenton
1mo
4
55
Rogue AGI Embodies Valuable Intellectual Property
Mark Xu
1y
9
47
AI X-risk >35% mostly based on a recent peer-reviewed argument
michaelcohen
1mo
31
42
AI Neorealism: a threat model & success criterion for existential safety
davidad
5d
0
38
Vignettes Workshop (AI Impacts)
Daniel Kokotajlo
1y
3
309
A central AI alignment problem: capabilities generalization, and the sharp left turn
So8res
6mo
48
87
Refining the Sharp Left Turn threat model, part 1: claims and mechanisms
Vika
4mo
3
70
We may be able to see sharp left turns coming
Ethan Perez
3mo
26
33
It matters when the first sharp left turn happens
Adam Jermyn
2mo
9
31
Refining the Sharp Left Turn threat model, part 2: applying alignment techniques
Vika
25d
4
14
How is the "sharp left turn defined"?
Chris_Leong
12d
3