This website requires javascript to properly function. Consider activating javascript to get access to all site functionality.
AI ALIGNMENT FORUM
Tags
AF
Login
AI Risk
Edit
History
Discussion
(0)
Help improve this page
(2 flags)
AI Risk
is analysis of the risks associated with building powerful AI systems.
Posts tagged
AI Risk
Most Relevant
3
62
What failure looks like
Paul Christiano
2y
27
Review
3
17
Specification gaming examples in AI
Vika
3y
8
4
17
Intuitions about goal-directed behavior
Rohin Shah
2y
5
3
38
What can the principal-agent literature tell us about AI risk?
Alexis Carlier
1y
11
2
13
Will OpenAI's work unintentionally increase existential risks related to AI?
Q
Adam Shimi
,
Matthew "Vaniver" Graves
5mo
Q
41
1
34
Developmental Stages of GPTs
orthonormal
6mo
27
1
19
Are minimal circuits deceptive?
Evan Hubinger
1y
8
1
52
Debate on Instrumental Convergence between LeCun, Russell, Bengio, Zador, and More
Ben Pace
1y
15
Review
1
60
An overview of 11 proposals for building safe advanced AI
Evan Hubinger
8mo
24
1
50
Risks from Learned Optimization: Introduction
Evan Hubinger
,
Chris van Merwijk
,
Vladimir Mikulik
,
Joar Skalse
,
Scott Garrabrant
2y
29
Review
1
28
Disentangling arguments for the importance of AI safety
Richard Ngo
2y
15
1
45
AI Alignment 2018-19 Review
Rohin Shah
1y
6
1
34
Soft takeoff can still lead to decisive strategic advantage
Daniel Kokotajlo
1y
32
Review
1
42
AI Safety "Success Stories"
Wei Dai
1y
11
Review
1
32
The Fusion Power Generator Scenario
johnswentworth
5mo
8