Go Back
You can't go any further
You can't go any further
meritocratic
regular
democratic
hot
top
alive
2 posts
Seed AI
161 posts
AI Risk
33
Wanted: backup plans for "seed AI turns out to be easy"
Wei_Dai
11y
64
9
Levels of AI Self-Improvement
avturchin
4y
0
58
Who are some prominent reasonable people who are confident that AI won't kill everyone?
Optimization Process
15d
40
93
AI will change the world, but won’t take it over by playing “3-dimensional chess”.
boazbarak
28d
86
87
Meta AI announces Cicero: Human-Level Diplomacy play (with dialogue)
Jacy Reese Anthis
28d
64
217
Counterarguments to the basic AI x-risk case
KatjaGrace
2mo
122
140
Worlds Where Iterative Design Fails
johnswentworth
3mo
26
26
Why are we sure that AI will "want" something?
shminux
3mo
58
59
AI Safety Seems Hard to Measure
HoldenKarnofsky
12d
5
405
AGI Ruin: A List of Lethalities
Eliezer Yudkowsky
6mo
653
17
Aligned Behavior is not Evidence of Alignment Past a Certain Level of Intelligence
Ronny Fernandez
15d
5
80
What does it mean for an AGI to be 'safe'?
So8res
2mo
32
75
Oversight Misses 100% of Thoughts The AI Does Not Think
johnswentworth
4mo
49
11
Is there any policy for a fair treatment of AIs whose friendliness is in doubt?
nahoj
1mo
9
109
Niceness is unnatural
So8res
2mo
18
87
The alignment problem from a deep learning perspective
Richard_Ngo
4mo
13