RSS

Daniel_Dewey

Karma: 303

My cur­rent thoughts on MIRI’s “highly re­li­able agent de­sign” work

Daniel_DeweyJul 7, 2017, 1:17 AM
60 points
59 comments19 min readEA link

How I missed my pledge and how I’m fix­ing it

Daniel_DeweyOct 10, 2016, 12:06 AM
21 points
9 comments2 min readEA link

Three ar­eas of re­search on the su­per­in­tel­li­gence con­trol problem

Daniel_DeweyNov 13, 2015, 6:11 PM
10 points
0 comments1 min readEA link

How much does work in AI safety help the world?

Daniel_DeweyAug 14, 2015, 10:32 PM
6 points
20 comments2 min readEA link

Effec­tive Altru­ism Global SF panel on AI: ques­tion sub­mis­sions thread

Daniel_DeweyJul 20, 2015, 7:34 PM
6 points
12 comments1 min readEA link

Re­search po­si­tion at Fu­ture of Hu­man­ity Institute

Daniel_DeweyApr 15, 2015, 11:46 AM
7 points
0 comments1 min readEA link

Re­quest for pro­pos­als for Musk/​FLI AI re­search grants

Daniel_DeweyFeb 6, 2015, 2:46 PM
5 points
2 comments2 min readEA link