Go Back
Choose this branch
Choose this branch
meritocratic
regular
democratic
hot
top
alive
21 posts
Threat Models
Sharp Left Turn
8 posts
Technological Unemployment
Multipolar Scenarios
42
AI Neorealism: a threat model & success criterion for existential safety
davidad
5d
0
148
Clarifying AI X-risk
zac_kenton
1mo
23
14
How is the "sharp left turn defined"?
Chris_Leong
12d
3
68
Threat Model Literature Review
zac_kenton
1mo
4
31
Refining the Sharp Left Turn threat model, part 2: applying alignment techniques
Vika
25d
4
309
A central AI alignment problem: capabilities generalization, and the sharp left turn
So8res
6mo
48
47
AI X-risk >35% mostly based on a recent peer-reviewed argument
michaelcohen
1mo
31
165
AI Could Defeat All Of Us Combined
HoldenKarnofsky
6mo
29
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
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
437
What failure looks like
paulfchristiano
3y
49
33
How much white collar work could be automated using existing ML models?
AM
6mo
4
20
Why multi-agent safety is important
Akbir Khan
6mo
2
6
How would two superintelligent AIs interact, if they are unaligned with each other?
Nathan1123
4mo
6
39
Value of the Long Tail
johnswentworth
2y
7
20
In a multipolar scenario, how do people expect systems to be trained to interact with systems developed by other labs?
JesseClifton
2y
6
28
Conversational Presentation of Why Automation is Different This Time
ryan_b
4y
26
14
Equilibrium and prior selection problems in multipolar deployment
JesseClifton
2y
11
6
Superintelligence 17: Multipolar scenarios
KatjaGrace
7y
38