Archive
Sequences
About
Search
Log In
Questions
Events
Shortform
Alignment Forum
AF Comments
Home
Featured
All
Tags
Recent
Comments
RSS
Richard_Ngo
Karma:
18,789
Formerly alignment and governance researcher at DeepMind and OpenAI. Now independent.
All
Posts
Comments
New
Top
Old
Page
1
Well-foundedness as an organizing principle of healthy minds and societies
Richard_Ngo
7 Apr 2025 0:31 UTC
35
points
7
comments
6
min read
LW
link
(www.mindthefuture.info)
Third-wave AI safety needs sociopolitical thinking
Richard_Ngo
27 Mar 2025 0:55 UTC
99
points
23
comments
26
min read
LW
link
Towards a scale-free theory of intelligent agency
Richard_Ngo
21 Mar 2025 1:39 UTC
96
points
44
comments
13
min read
LW
link
(www.mindthefuture.info)
Elite Coordination via the Consensus of Power
Richard_Ngo
19 Mar 2025 6:56 UTC
92
points
15
comments
12
min read
LW
link
(www.mindthefuture.info)
Trojan Sky
Richard_Ngo
11 Mar 2025 3:14 UTC
245
points
39
comments
12
min read
LW
link
(www.narrativeark.xyz)
Power Lies Trembling: a three-book review
Richard_Ngo
22 Feb 2025 22:57 UTC
213
points
27
comments
15
min read
LW
link
(www.mindthefuture.info)
The Gentle Romance
Richard_Ngo
19 Jan 2025 18:29 UTC
242
points
46
comments
15
min read
LW
link
(www.asimov.press)
From the Archives: a story
Richard_Ngo
27 Dec 2024 16:36 UTC
20
points
1
comment
16
min read
LW
link
(www.narrativeark.xyz)
Epistemic status: poetry (and other poems)
Richard_Ngo
21 Nov 2024 18:13 UTC
51
points
5
comments
2
min read
LW
link
(www.narrativeark.xyz)
Why I’m not a Bayesian
Richard_Ngo
6 Oct 2024 15:22 UTC
211
points
101
comments
10
min read
LW
link
(www.mindthefuture.info)
Defining alignment research
Richard_Ngo
19 Aug 2024 20:42 UTC
92
points
23
comments
7
min read
LW
link
Green and golden: a meditation
Richard_Ngo
18 Aug 2024 1:36 UTC
21
points
0
comments
3
min read
LW
link
(www.narrativeark.xyz)
Twitter thread on open-source AI
Richard_Ngo
31 Jul 2024 0:26 UTC
33
points
6
comments
2
min read
LW
link
(x.com)
Twitter thread on AI takeover scenarios
Richard_Ngo
31 Jul 2024 0:24 UTC
37
points
0
comments
2
min read
LW
link
(x.com)
Twitter thread on AI safety evals
Richard_Ngo
31 Jul 2024 0:18 UTC
63
points
3
comments
2
min read
LW
link
(x.com)
Twitter thread on politics of AI safety
Richard_Ngo
31 Jul 2024 0:00 UTC
35
points
2
comments
1
min read
LW
link
(x.com)
Coalitional agency
Richard_Ngo
22 Jul 2024 0:09 UTC
56
points
6
comments
6
min read
LW
link
A more systematic case for inner misalignment
Richard_Ngo
20 Jul 2024 5:03 UTC
31
points
4
comments
5
min read
LW
link
Towards more cooperative AI safety strategies
Richard_Ngo
16 Jul 2024 4:36 UTC
215
points
133
comments
4
min read
LW
link
A simple case for extreme inner misalignment
Richard_Ngo
13 Jul 2024 15:40 UTC
84
points
41
comments
7
min read
LW
link
Back to top
Next