Go Back
Choose this branch
Choose this branch
meritocratic
regular
democratic
hot
top
alive
195 posts
AI Risk
Threat Models
Sharp Left Turn
Multipolar Scenarios
Technological Unemployment
Missing Moods
Seed AI
108 posts
Whole Brain Emulation
Reading Group
Economic Consequences of AGI
Superintelligence
Q&A (format)
Automation
1043
AGI Ruin: A List of Lethalities
Eliezer Yudkowsky
6mo
653
1039
Where I agree and disagree with Eliezer
paulfchristiano
6mo
205
455
Counterarguments to the basic AI x-risk case
KatjaGrace
2mo
122
437
What failure looks like
paulfchristiano
3y
49
432
Discussion with Eliezer Yudkowsky on AGI interventions
Rob Bensinger
1y
257
309
A central AI alignment problem: capabilities generalization, and the sharp left turn
So8res
6mo
48
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
217
Slow motion videos as AI risk intuition pumps
Andrew_Critch
6mo
36
205
[RETRACTED] It's time for EA leadership to pull the short-timelines fire alarm.
Not Relevant
8mo
165
170
AGI ruin scenarios are likely (and disjunctive)
So8res
4mo
37
165
On A List of Lethalities
Zvi
6mo
48
165
AI Could Defeat All Of Us Combined
HoldenKarnofsky
6mo
29
150
Superintelligence FAQ
Scott Alexander
6y
16
192
Whole Brain Emulation: No Progress on C. elgans After 10 Years
niconiconi
1y
77
130
All AGI safety questions welcome (especially basic ones) [July 2022]
plex
5mo
130
117
We Haven't Uploaded Worms
jefftk
7y
19
100
All AGI Safety questions welcome (especially basic ones) [~monthly thread]
Robert Miles
1mo
100
97
Transcription of Eliezer's January 2010 video Q&A
curiousepic
11y
9
94
Intermittent Distillations #4: Semiconductors, Economics, Intelligence, and Technological Progress.
Mark Xu
1y
9
86
Introducing the AI Alignment Forum (FAQ)
habryka
4y
8
69
Human Mimicry Mainly Works When We’re Already Close
johnswentworth
4mo
16
64
Argument against 20% GDP growth from AI within 10 years [Linkpost]
aogara
3mo
21
62
Hacking the CEV for Fun and Profit
Wei_Dai
12y
207
60
Three AI Safety Related Ideas
Wei_Dai
4y
38
54
[Fiction] IO.SYS
DataPacRat
3y
4
53
Q&A with Shane Legg on risks from AI
XiXiDu
11y
24
51
Q&A with Jürgen Schmidhuber on risks from AI
XiXiDu
11y
45