Richard_Ngo

Karma: 18,333

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

Third-wave AI safety needs sociopolitical thinking

Richard_NgoMar 27, 2025, 12:55 AM

97 points

23 comments26 min readLW link

Towards a scale-free theory of intelligent agency

Richard_NgoMar 21, 2025, 1:39 AM

91 points

21 comments13 min readLW link

(www.mindthefuture.info)

Elite Coordination via the Consensus of Power

Richard_NgoMar 19, 2025, 6:56 AM

90 points

15 comments12 min readLW link

(www.mindthefuture.info)

Trojan Sky

Richard_NgoMar 11, 2025, 3:14 AM

216 points

39 comments12 min readLW link

(www.narrativeark.xyz)

Power Lies Trembling: a three-book review

Richard_NgoFeb 22, 2025, 10:57 PM

145 points

7 comments15 min readLW link

(www.mindthefuture.info)

The Gentle Romance

Richard_NgoJan 19, 2025, 6:29 PM

231 points

46 comments15 min readLW link

(www.asimov.press)

From the Archives: a story

Richard_NgoDec 27, 2024, 4:36 PM

20 points

1 comment16 min readLW link

(www.narrativeark.xyz)

Epistemic status: poetry (and other poems)

Richard_NgoNov 21, 2024, 6:13 PM

51 points

5 comments2 min readLW link

(www.narrativeark.xyz)

Why I’m not a Bayesian

Richard_NgoOct 6, 2024, 3:22 PM

204 points

101 comments10 min readLW link

(www.mindthefuture.info)

Defining alignment research

Richard_NgoAug 19, 2024, 8:42 PM

92 points

23 comments7 min readLW link

Green and golden: a meditation

Richard_NgoAug 18, 2024, 1:36 AM

20 points

0 comments3 min readLW link

(www.narrativeark.xyz)

Twitter thread on open-source AI

Richard_NgoJul 31, 2024, 12:26 AM

33 points

6 comments2 min readLW link

(x.com)

Twitter thread on AI takeover scenarios

Richard_NgoJul 31, 2024, 12:24 AM

37 points

0 comments2 min readLW link

(x.com)

Twitter thread on AI safety evals

Richard_NgoJul 31, 2024, 12:18 AM

63 points

3 comments2 min readLW link

(x.com)

Twitter thread on politics of AI safety

Richard_NgoJul 31, 2024, 12:00 AM

35 points

2 comments1 min readLW link

(x.com)

Coalitional agency

Richard_NgoJul 22, 2024, 12:09 AM

56 points

6 comments6 min readLW link

A more systematic case for inner misalignment

Richard_NgoJul 20, 2024, 5:03 AM

31 points

4 comments5 min readLW link

Towards more cooperative AI safety strategies

Richard_NgoJul 16, 2024, 4:36 AM

210 points

133 comments4 min readLW link

A simple case for extreme inner misalignment

Richard_NgoJul 13, 2024, 3:40 PM

84 points

41 comments7 min readLW link

The Minority Coalition

Richard_NgoJun 24, 2024, 8:01 PM

103 points

9 comments5 min readLW link

(www.narrativeark.xyz)