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
Top Questions
24
How "honest" is GPT-3?
Q
Abram Demski
,
gwern
4d
Q
4
21
Best reasons for pessimism about impact of impact measures?
Q
Alex Turner
,
Matthew "Vaniver" Graves
1y
Q
44
18
How common is it for one entity to have a 3+ year technological lead on its nearest competitor?
Q
Daniel Kokotajlo
8mo
Q
0
16
Does Agent-like Behavior Imply Agent-like Architecture?
Q
Scott Garrabrant
1y
Q
2
19
How does Gradient Descent Interact with Goodhart?
Q
Scott Garrabrant
,
Vanessa Kosoy
1y
Q
4
Recent Activity
24
How "honest" is GPT-3?
Q
Abram Demski
,
gwern
4d
Q
4
4
Have general decomposers been formalized?
Q
Quinn
15d
Q
0
4
What are the high-level approaches to AI alignment?
Q
G Gordon Worley III
,
Issa Rice
1mo
Q
13
7
When is CDT Dutch-Bookable?
Q
Abram Demski
1y
Q
2
8
How does iterated amplification exceed human abilities?
Q
Issa Rice
,
Rohin Shah
2mo
Q
9
8
How should potential AI alignment researchers gauge whether the field is right for them?
Q
Alex Turner
2mo
Q
3
5
What is the alternative to intent alignment called?
Q
ricraz
2mo
Q
3
4
What is the subjective experience of free will for agents?
Q
G Gordon Worley III
3mo
Q
3
15
What are the most plausible "AI Safety warning shot" scenarios?
Q
Daniel Kokotajlo
,
Paul Christiano
4mo
Q
4
4
Name of Problem?
Q
johnswentworth
4mo
Q
13
6
[Meta] Do you want AIS Webinars?
Q
Linda Linsefors
4mo
Q
2
8
Positive Feedback -> Optimization?
Q
johnswentworth
4mo
Q
4
