Go Back
Choose this branch
You can't go any further
meritocratic
regular
democratic
hot
top
alive
163 posts
AI Risk
Seed AI
3 posts
Missing Moods
77
AI Safety Seems Hard to Measure
HoldenKarnofsky
12d
5
455
Counterarguments to the basic AI x-risk case
KatjaGrace
2mo
122
64
Who are some prominent reasonable people who are confident that AI won't kill everyone?
Optimization Process
15d
40
1039
Where I agree and disagree with Eliezer
paulfchristiano
6mo
205
113
AI will change the world, but won’t take it over by playing “3-dimensional chess”.
boazbarak
28d
86
1043
AGI Ruin: A List of Lethalities
Eliezer Yudkowsky
6mo
653
103
Meta AI announces Cicero: Human-Level Diplomacy play (with dialogue)
Jacy Reese Anthis
28d
64
117
Am I secretly excited for AI getting weird?
porby
1mo
4
28
Apply to attend winter AI alignment workshops (Dec 28-30 & Jan 3-5) near Berkeley
Akash
19d
1
21
Aligned Behavior is not Evidence of Alignment Past a Certain Level of Intelligence
Ronny Fernandez
15d
5
87
Niceness is unnatural
So8res
2mo
18
148
Worlds Where Iterative Design Fails
johnswentworth
3mo
26
15
Race to the Top: Benchmarks for AI Safety
Isabella Duan
16d
2
170
AGI ruin scenarios are likely (and disjunctive)
So8res
4mo
37
52
Reflections on My Own Missing Mood
Conor Sullivan
8mo
25
31
What Caplan’s "Missing Mood" Heuristic Is Really For
AllAmericanBreakfast
1y
7
12
Five Missing Moods
mike_hawke
1y
3