AI ALIGNMENT FORUMrohinmshah
AF

User Profile

Ω34855108

Sequences

Value Learning

Alignment Newsletter

rohinmshah's Posts

sorted by new
All Posts
Frontpage
Curated
Questions
Events
Meta

Alignment Newsletter #42

10
Rohin Shah
2d9 min readShow Highlight
0

Following human norms

9
Rohin Shah
3d4 min readShow Highlight
0

Reward uncertainty

6
Rohin Shah
5d5 min readShow Highlight
0

[Link] Reframing Superintelligence: Comprehensive AI Services as General Intelligence

24
Rohin Shah
15d4 min readShow Highlight
20

Alignment Newsletter #41

7
Rohin Shah
6d10 min readShow Highlight
6

Human-AI Interaction

7
Rohin Shah
9d4 min readShow Highlight
0

AI safety without goal-directed behavior

12
Rohin Shah
16d3 min readShow Highlight
6

Will humans build goal-directed agents?

11
Rohin Shah
19d5 min readShow Highlight
15

What is narrow value learning?

6
Rohin Shah
13d1 min readShow Highlight
3

Alignment Newsletter #40

7
Rohin Shah
15d4 min readShow Highlight
0
Load More...  

rohinmshah's Comments