AI ALIGNMENT FORUMrohinmshah
AF

Rohin Shah

Ω73474229

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

Sequences

Value Learning

Alignment Newsletter

Rohin Shah's Posts

Sorted by New
14[AN #59] How arguments for AI risk have changed over time
Rohin Shah
8d
0
15Learning biases and rewards simultaneously
Rohin Shah
11d
3
19[AN #58] Mesa optimization: what it is, and why we should care
Rohin Shah
22d
1
13[AN #57] Why we should focus on robustness in AI safety, and the analogous problems in programming
Rohin Shah
1mo
14
9[AN #56] Should ML researchers stop running experiments before making hypotheses?
Rohin Shah
2mo
6
10[AN #55] Regulatory markets and international standards as a means of ensuring beneficial AI
Rohin Shah
2mo
0
10[AN #54] Boxing a finite-horizon AI system to keep it unambitious
Rohin Shah
3mo
0
23Alignment Newsletter One Year Retrospective
Rohin Shah
3mo
10
9Alignment Newsletter #52
Rohin Shah
3mo
1
10Alignment Newsletter #51
Rohin Shah
3mo
0
Load More

Rohin Shah's Comments