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
319
What failure looks like
paulfchristiano
3y
49
210
Another (outer) alignment failure story
paulfchristiano
1y
38
203
What Multipolar Failure Looks Like, and Robust Agent-Agnostic Processes (RAAPs)
Andrew_Critch
1y
60
168
AI Could Defeat All Of Us Combined
HoldenKarnofsky
6mo
29
110
Less Realistic Tales of Doom
Mark Xu
1y
13
102
Clarifying AI X-risk
zac_kenton
1mo
23
79
What Failure Looks Like: Distilling the Discussion
Ben Pace
2y
14
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
55
Threat Model Literature Review
zac_kenton
1mo
4
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
253
A central AI alignment problem: capabilities generalization, and the sharp left turn
So8res
6mo
48
71
Refining the Sharp Left Turn threat model, part 1: claims and mechanisms
Vika
4mo
3
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
35
It matters when the first sharp left turn happens
Adam Jermyn
2mo
9
13
How is the "sharp left turn defined"?
Chris_Leong
12d
3