AI ALIGNMENT FORUMrohinmshah
AF

Rohin Shah

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

8[AN #64]: Using Deep RL and Reward Uncertainty to Incentivize Preference Learning

7d

6

14[AN #63] How architecture search, meta learning, and environment design could lead to general intelligence

13d

3

13[AN #62] Are adversarial examples caused by real but imperceptible features?

1mo

8

13Call for contributors to the Alignment Newsletter

1mo

0

23Clarifying some key hypotheses in AI alignment

Ben Cottier, Rohin Shah

1mo

1

10[AN #60] A new AI challenge: Minecraft agents that assist human players in creative mode

2mo

1

14[AN #59] How arguments for AI risk have changed over time

2mo

0

16Learning biases and rewards simultaneously

3mo

3

19[AN #58] Mesa optimization: what it is, and why we should care

3mo

1

13[AN #57] Why we should focus on robustness in AI safety, and the analogous problems in programming

4mo

14

Rohin Shah's Comments