RSS

G Gordon Worley III

Karma: 2,319
AllPostsComments
NewTop
Page 1

HLAI 2018 Talks

gworley
17 Sep 2018 18:13 UTC
12 points
2 comments1 min readLW link
(slideslive.com)

HLAI 2018 Field Report

gworley
29 Aug 2018 0:11 UTC
44 points
12 comments5 min readLW link

A developmentally-situated approach to teaching normative behavior to AI

gworley
17 Aug 2018 18:44 UTC
12 points
0 comments8 min readLW link

Solving the AI Race Finalists

gworley
19 Jul 2018 21:04 UTC
27 points
0 comments1 min readLW link
(medium.com)

Look Under the Light Post

gworley
16 Jul 2018 22:19 UTC
25 points
8 comments4 min readLW link

Idea: Open Access AI Safety Journal

gworley
23 Mar 2018 18:27 UTC
64 points
11 comments1 min readLW link

Robustness to fundamental uncertainty in AGI alignment

gworley
27 Jul 2018 0:41 UTC
7 points
1 comment1 min readLW link
(arxiv.org)

Thoughts on “AI safety via debate”

gworley
10 May 2018 0:44 UTC
33 points
4 comments5 min readLW link

RFC: Philosophical Conservatism in AI Alignment Research

gworley
15 May 2018 3:29 UTC
27 points
13 comments1 min readLW link

RFC: Meta-ethical uncertainty in AGI alignment

gworley
8 Jun 2018 20:56 UTC
18 points
6 comments3 min readLW link

The Incoherence of Honesty

gworley
8 Jun 2018 2:28 UTC
22 points
16 comments3 min readLW link

Aligned AI May Depend on Moral Facts

gworley
15 Jun 2018 1:33 UTC
9 points
11 comments1 min readLW link

Evaluating Existing Approaches to AGI Alignment

gworley
27 Mar 2018 19:57 UTC
22 points
0 comments4 min readLW link
(mapandterritory.org)

Self-regulation of safety in AI research

gworley
25 Feb 2018 23:17 UTC
33 points
6 comments2 min readLW link

RFC: Mental phenomena in AGI alignment

gworley
5 Jul 2018 20:52 UTC
13 points
16 comments5 min readLW link

How safe “safe” AI development?

gworley
28 Feb 2018 23:21 UTC
26 points
1 comment1 min readLW link

Form and Feedback in Phenomenology

gworley
24 Jan 2018 19:42 UTC
29 points
1 comment1 min readLW link

The Leading and Trailing Edges of Development

gworley
26 Apr 2018 18:02 UTC
24 points
9 comments2 min readLW link

Epistemic Circularity

gworley
23 May 2018 21:00 UTC
5 points
2 comments1 min readLW link

Safety in Machine Learning

gworley
29 May 2018 18:54 UTC
17 points
0 comments1 min readLW link