Go Back
Choose this branch
You can't go any further
meritocratic
regular
democratic
hot
top
alive
95 posts
Newsletters
Gaming (videogames/tabletop)
1 posts
28
[AN #112]: Engineering a Safer World
Rohin Shah
2y
2
5
The Alignment Newsletter #4: 04/30/18
Rohin Shah
4y
0
19
Alignment Newsletter #21
Rohin Shah
4y
0
15
Alignment Newsletter #42
Rohin Shah
3y
1
9
Alignment Newsletter #28
Rohin Shah
4y
0
22
[AN #81]: Universality as a potential solution to conceptual difficulties in intent alignment
Rohin Shah
2y
4
14
[AN #56] Should ML researchers stop running experiments before making hypotheses?
Rohin Shah
3y
8
5
The Alignment Newsletter #7: 05/21/18
Rohin Shah
4y
0
14
Alignment Newsletter #44
Rohin Shah
3y
0
24
[AN #87]: What might happen as deep learning scales even further?
Rohin Shah
2y
0
23
[AN #84] Reviewing AI alignment work in 2018-19
Rohin Shah
2y
0
14
[AN #82]: How OpenAI Five distributed their training computation
Rohin Shah
2y
0
13
[AN #89]: A unifying formalism for preference learning algorithms
Rohin Shah
2y
0
146
Quintin's alignment papers roundup - week 1
Quintin Pope
3mo
5
60
Alignment Newsletter #13: 07/02/18
Rohin Shah
4y
12