Richard_Ngo

Karma: 17,313

Formerly alignment and governance researcher at DeepMind and OpenAI. Now independent.

The Gentle Romance

Richard_Ngo19 Jan 2025 18:29 UTC

170 points

20 comments15 min readLW link

(www.asimov.press)

From the Archives: a story

Richard_Ngo27 Dec 2024 16:36 UTC

18 points

1 comment16 min readLW link

(www.narrativeark.xyz)

Epistemic status: poetry (and other poems)

Richard_Ngo21 Nov 2024 18:13 UTC

50 points

5 comments2 min readLW link

(www.narrativeark.xyz)

Why I’m not a Bayesian

Richard_Ngo6 Oct 2024 15:22 UTC

189 points

93 comments10 min readLW link

(www.mindthefuture.info)

Defining alignment research

Richard_Ngo19 Aug 2024 20:42 UTC

91 points

23 comments7 min readLW link

Green and golden: a meditation

Richard_Ngo18 Aug 2024 1:36 UTC

20 points

0 comments3 min readLW link

(www.narrativeark.xyz)

Twitter thread on open-source AI

Richard_Ngo31 Jul 2024 0:26 UTC

33 points

6 comments2 min readLW link

(x.com)

Twitter thread on AI takeover scenarios

Richard_Ngo31 Jul 2024 0:24 UTC

37 points

0 comments2 min readLW link

(x.com)

Twitter thread on AI safety evals

Richard_Ngo31 Jul 2024 0:18 UTC

62 points

3 comments2 min readLW link

(x.com)

Twitter thread on politics of AI safety

Richard_Ngo31 Jul 2024 0:00 UTC

35 points

2 comments1 min readLW link

(x.com)

Coalitional agency

Richard_Ngo22 Jul 2024 0:09 UTC

56 points

6 comments6 min readLW link

A more systematic case for inner misalignment

Richard_Ngo20 Jul 2024 5:03 UTC

31 points

4 comments5 min readLW link

Towards more cooperative AI safety strategies

Richard_Ngo16 Jul 2024 4:36 UTC

208 points

133 comments4 min readLW link

A simple case for extreme inner misalignment

Richard_Ngo13 Jul 2024 15:40 UTC

83 points

41 comments7 min readLW link

The Minority Coalition

Richard_Ngo24 Jun 2024 20:01 UTC

101 points

9 comments5 min readLW link

(www.narrativeark.xyz)

CIV: a story

Richard_Ngo15 Jun 2024 22:36 UTC

97 points

6 comments9 min readLW link

(www.narrativeark.xyz)

Tinker

Richard_Ngo16 Apr 2024 18:26 UTC

38 points

0 comments1 min readLW link

(press.asimov.com)

Measuring Coherence of Policies in Toy Environments

dx26 and Richard_Ngo

18 Mar 2024 17:59 UTC

59 points

9 comments14 min readLW link

Notes from a Prompt Factory

Richard_Ngo10 Mar 2024 5:13 UTC

102 points

19 comments9 min readLW link

(www.narrativeark.xyz)

Every “Every Bay Area House Party” Bay Area House Party

Richard_Ngo16 Feb 2024 18:53 UTC

178 points

6 comments4 min readLW link