This website requires javascript to properly function. Consider activating javascript to get access to all site functionality.
AI ALIGNMENT FORUM
AF
Login
Home
Library
Questions
All Posts
About
All Posts
Sorted by Magic (New & Upvoted)
Timeframe:
All Time
Daily
Weekly
Monthly
Yearly
Sorted by:
Magic (New & Upvoted)
Recent Comments
New
Old
Top
Filtered by:
All Posts
Questions
Meta
Show Low Karma
Wednesday, February 24th 2021
Wed, Feb 24th 2021
Frontpage Posts
9
[AN #139]: How the simplicity of reality explains the success of neural nets
Rohin Shah
2h
0
Tuesday, February 23rd 2021
Tue, Feb 23rd 2021
No posts for February 23rd 2021
Monday, February 22nd 2021
Mon, Feb 22nd 2021
No posts for February 22nd 2021
Sunday, February 21st 2021
Sun, Feb 21st 2021
No posts for February 21st 2021
Saturday, February 20th 2021
Sat, Feb 20th 2021
No posts for February 20th 2021
Friday, February 19th 2021
Fri, Feb 19th 2021
No posts for February 19th 2021
Thursday, February 18th 2021
Thu, Feb 18th 2021
Frontpage Posts
32
Utility Maximization = Description Length Minimization
johnswentworth
6d
7
18
AXRP Episode 4 - Risks from Learned Optimization with Evan Hubinger
DanielFilan
7d
8
10
Formal Solution to the Inner Alignment Problem
michaelcohen
6d
46
Wednesday, February 17th 2021
Wed, Feb 17th 2021
Frontpage Posts
9
[AN #138]: Why AI governance should find problems rather than just solving them
Rohin Shah
7d
0
4
Safely controlling the AGI agent reward function
Koen Holtman
7d
0
3
Graphical World Models, Counterfactuals, and Machine Learning Agents
Koen Holtman
7d
2
Tuesday, February 16th 2021
Tue, Feb 16th 2021
Frontpage Posts
23
Suggestions of posts on the AF to review
Q
Adam Shimi
,
johnswentworth
8d
Q
13
10
Cartesian frames as generalised models
Stuart Armstrong
8d
0
7
Generalised models as a category
Stuart Armstrong
8d
3
5
Disentangling Corrigibility: 2015-2021
Koen Holtman
8d
0
Monday, February 15th 2021
Mon, Feb 15th 2021
No posts for February 15th 2021
Load More Days