AI ALIGNMENT FORUMrohinmshah
AF

Rohin Shah

PhD student at the Center for Human-Compatible AI. Creator of the Alignment Newsletter. http://rohinshah.com/

Sequences

Rohin Shah's Posts

Sorted by New
7[AN #74]: Separating beneficial AI into competence, alignment, and coping with impacts
Rohin Shah
2h
0
8[AN #73]: Detecting catastrophic failures by learning how agents tend to break
Rohin Shah
7d
0
14[AN #72]: Alignment, robustness, methodology, and system building as research priorities for AI safety
Rohin Shah
14d
0
8[AN #71]: Avoiding reward tampering through current-RF optimization
Rohin Shah
21d
0
13[AN #70]: Agents that help humans who are still learning about their own preferences
Rohin Shah
1mo
0
19[Link]Human-AI Collaboration
Rohin Shah
1mo
4
20[AN #69] Stuart Russell's new book on why we need to replace the standard model of AI
Rohin Shah
1mo
10
11[AN #68]: The attainable utility theory of impact
Rohin Shah
1mo
0
12[AN #67]: Creating environments in which to study inner alignment failures
Rohin Shah
1mo
0
9[AN #66]: Decomposing robustness into capability robustness and alignment robustness
Rohin Shah
2mo
1

Rohin Shah's Comments