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
68
Risks from AI persuasion
Beth Barnes
12mo
15
74
Persuasion Tools: AI takeover without AGI or agency?
Daniel Kokotajlo
2y
24
7
Multiple AIs in boxes, evaluating each other's alignment
Moebius314
6mo
0
116
The Strangest Thing An AI Could Tell You
Eliezer Yudkowsky
13y
605
73
I attempted the AI Box Experiment again! (And won - Twice!)
Tuxedage
9y
168
77
I attempted the AI Box Experiment (and lost)
Tuxedage
9y
245
50
How To Win The AI Box Experiment (Sometimes)
pinkgothic
7y
21
58
I played the AI Box Experiment again! (and lost both games)
Tuxedage
9y
123
43
How to escape from your sandbox and from your hardware host
PhilGoetz
7y
28
15
Is there a simple parameter that controls human working memory capacity, which has been set tragically low?
Liron
3y
8
54
Cryptographic Boxes for Unfriendly AI
paulfchristiano
12y
162
16
AI Alignment Prize: Super-Boxing
X4vier
4y
6
12
Sandboxing by Physical Simulation?
moridinamael
4y
4
25
AI box: AI has one shot at avoiding destruction - what might it say?
ancientcampus
9y
355
11
Conditions for Superrationality-motivated Cooperation in a one-shot Prisoner's Dilemma
Jim Buhler
1d
2
11
Prosaic misalignment from the Solomonoff Predictor
Cleo Nardo
11d
0
38
The Solomonoff prior is malign. It's not a big deal.
Charlie Steiner
3mo
9
47
[Repost] Non-Nashian Game Theory: A Normal-Form Primer
Ghislain Fourny
6mo
14
108
A new acausal trading platform: RobinShould
Matthew Barnett
1y
5
2
How does acausal trade work in a deterministic multiverse?
sisyphus
1mo
13
41
Superrational Agents Kelly Bet Influence!
abramdemski
1y
5
58
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
47
Counterfactual Oracles = online supervised learning with random selection of training episodes
Wei_Dai
3y
26
72
[REPOST] The Demiurge’s Older Brother
Scott Alexander
5y
2
51
Book Review: AI Safety and Security
Michaël Trazzi
4y
2
25
Breaking Oracles: superrationality and acausal trade
Stuart_Armstrong
3y
15
22
Analysing: Dangerous messages from future UFAI via Oracles
Stuart_Armstrong
3y
16