This website requires javascript to properly function. Consider activating javascript to get access to all site functionality.
AI ALIGNMENT FORUM
AF
Login
Nominated Posts for the 2018 Review
Sort by: fewest nominations
10
The Steering Problem
Paul Christiano
2y
2
1
26
Coherence arguments do not imply goal-directed behavior
Rohin Shah
1y
45
2
19
Clarifying "AI Alignment"
Paul Christiano
2y
73
2
11
Toward a New Technical Explanation of Technical Explanation
Abram Demski
2y
2
2
3
Specification gaming examples in AI
Vika
2y
8
2
13
Bottle Caps Aren't Optimisers
DanielFilan
2y
9
2
8
Open question: are minimal circuits daemon-free?
Paul Christiano
2y
9
2
11
An Untrollable Mathematician Illustrated
Abram Demski
2y
2
2
23
Towards a New Impact Measure
Alex Turner
2y
119
2
37
2018 AI Alignment Literature Review and Charity Comparison
Larks
1y
4
2
3
Optimization Amplifies
Scott Garrabrant
2y
3
2
9
Paul's research agenda FAQ
Alex Zhu
2y
31
2
6
Beyond Astronomical Waste
Wei Dai
2y
9
2
31
Realism about rationality
ricraz
2y
50
3
8
Robustness to Scale
Scott Garrabrant
2y
6
3
11
Challenges to Christiano’s capability amplification proposal
Eliezer Yudkowsky
2y
2
3
8
Arguments about fast takeoff
Paul Christiano
2y
1
4
22
The Rocket Alignment Problem
Eliezer Yudkowsky
2y
5
6
35
Embedded Agents
Abram Demski
,
Scott Garrabrant
2y
7
6
2018 Review Discussion
Load More