Go Back
Choose this branch
Choose this branch
meritocratic
regular
democratic
hot
top
alive
166 posts
AI Risk
Missing Moods
Seed AI
29 posts
Threat Models
Sharp Left Turn
Multipolar Scenarios
Technological Unemployment
64
Who are some prominent reasonable people who are confident that AI won't kill everyone?
Optimization Process
15d
40
113
AI will change the world, but won’t take it over by playing “3-dimensional chess”.
boazbarak
28d
86
103
Meta AI announces Cicero: Human-Level Diplomacy play (with dialogue)
Jacy Reese Anthis
28d
64
455
Counterarguments to the basic AI x-risk case
KatjaGrace
2mo
122
148
Worlds Where Iterative Design Fails
johnswentworth
3mo
26
36
Why are we sure that AI will "want" something?
shminux
3mo
58
77
AI Safety Seems Hard to Measure
HoldenKarnofsky
12d
5
1043
AGI Ruin: A List of Lethalities
Eliezer Yudkowsky
6mo
653
21
Aligned Behavior is not Evidence of Alignment Past a Certain Level of Intelligence
Ronny Fernandez
15d
5
64
What does it mean for an AGI to be 'safe'?
So8res
2mo
32
95
Oversight Misses 100% of Thoughts The AI Does Not Think
johnswentworth
4mo
49
19
Is there any policy for a fair treatment of AIs whose friendliness is in doubt?
nahoj
1mo
9
87
Niceness is unnatural
So8res
2mo
18
99
The alignment problem from a deep learning perspective
Richard_Ngo
4mo
13
47
AI X-risk >35% mostly based on a recent peer-reviewed argument
michaelcohen
1mo
31
148
Clarifying AI X-risk
zac_kenton
1mo
23
14
How is the "sharp left turn defined"?
Chris_Leong
12d
3
70
We may be able to see sharp left turns coming
Ethan Perez
3mo
26
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
33
It matters when the first sharp left turn happens
Adam Jermyn
2mo
9
68
Threat Model Literature Review
zac_kenton
1mo
4
87
Refining the Sharp Left Turn threat model, part 1: claims and mechanisms
Vika
4mo
3
6
How would two superintelligent AIs interact, if they are unaligned with each other?
Nathan1123
4mo
6
88
What Failure Looks Like: Distilling the Discussion
Ben Pace
2y
14
20
Why multi-agent safety is important
Akbir Khan
6mo
2
165
AI Could Defeat All Of Us Combined
HoldenKarnofsky
6mo
29
253
Another (outer) alignment failure story
paulfchristiano
1y
38