Go Back
Choose this branch
Choose this branch
meritocratic
regular
democratic
hot
top
alive
19 posts
AI Boxing (Containment)
AI Persuasion
79 posts
Oracle AI
Acausal Trade
Superrationality
Values handshakes
112
The Strangest Thing An AI Could Tell You
Eliezer Yudkowsky
13y
605
89
I attempted the AI Box Experiment (and lost)
Tuxedage
9y
245
88
I attempted the AI Box Experiment again! (And won - Twice!)
Tuxedage
9y
168
74
I played the AI Box Experiment again! (and lost both games)
Tuxedage
9y
123
64
Cryptographic Boxes for Unfriendly AI
paulfchristiano
12y
162
63
How To Win The AI Box Experiment (Sometimes)
pinkgothic
7y
21
61
Persuasion Tools: AI takeover without AGI or agency?
Daniel Kokotajlo
2y
24
60
Risks from AI persuasion
Beth Barnes
12mo
15
57
How to escape from your sandbox and from your hardware host
PhilGoetz
7y
28
31
AI box: AI has one shot at avoiding destruction - what might it say?
ancientcampus
9y
355
30
AI Box Log
Dorikka
10y
30
29
Dreams of Friendliness
Eliezer Yudkowsky
14y
81
20
Is there a simple parameter that controls human working memory capacity, which has been set tragically low?
Liron
3y
8
18
AI Alignment Prize: Super-Boxing
X4vier
4y
6
106
A new acausal trading platform: RobinShould
Matthew Barnett
1y
5
82
Hofstadter's Superrationality
gwern
10y
21
65
Results of $1,000 Oracle contest!
Stuart_Armstrong
2y
2
57
Contest: $1,000 for good questions to ask to an Oracle AI
Stuart_Armstrong
3y
156
55
Counterfactual Oracles = online supervised learning with random selection of training episodes
Wei_Dai
3y
26
48
Book Review: AI Safety and Security
Michaël Trazzi
4y
2
47
Superrational Agents Kelly Bet Influence!
abramdemski
1y
5
42
Acausal romance
lukeprog
10y
37
40
Superrationality and network flow control
Alex Flint
9y
11
37
[REPOST] The Demiurge’s Older Brother
Scott Alexander
5y
2
37
The Solomonoff prior is malign. It's not a big deal.
Charlie Steiner
3mo
9
33
A taxonomy of Oracle AIs
lukeprog
10y
54
33
[Repost] Non-Nashian Game Theory: A Normal-Form Primer
Ghislain Fourny
6mo
14
32
Reflective oracles as a solution to the converse Lawvere problem
SamEisenstat
4y
0