richard_ngo

Karma: 7,503

Former AI safety research engineer, now AI governance researcher at OpenAI. Blog: thinkingcomplete.blogspot.com

Defining alignment research

richard_ngo19 Aug 2024 22:49 UTC

48 points

1 comment1 min readEA link

Twitter thread on open-source AI

richard_ngo31 Jul 2024 0:30 UTC

32 points

0 comments1 min readEA link

(x.com)

Twitter thread on AI safety evals

richard_ngo31 Jul 2024 0:29 UTC

38 points

2 comments1 min readEA link

(x.com)

Towards more cooperative AI safety strategies

richard_ngo16 Jul 2024 4:36 UTC

62 points

5 comments1 min readEA link

You must not fool yourself, and you are the easiest person to fool

richard_ngo8 Jul 2023 14:05 UTC

25 points

0 comments1 min readEA link

Agency begets agency

richard_ngo6 Jul 2023 13:09 UTC

28 points

1 comment1 min readEA link

Cultivate an obsession with the object level

richard_ngo7 Jun 2023 1:39 UTC

24 points

0 comments1 min readEA link

Coercion is an adaptation to scarcity; trust is an adaptation to abundance

richard_ngo23 May 2023 18:14 UTC

38 points

5 comments1 min readEA link

Self-leadership and self-love dissolve anger and trauma

richard_ngo22 May 2023 22:30 UTC

29 points

0 comments1 min readEA link

Trust develops gradually via making bids and setting boundaries

richard_ngo19 May 2023 22:16 UTC

25 points

0 comments1 min readEA link

Resolving internal conflicts requires listening to what parts want

richard_ngo19 May 2023 0:04 UTC

23 points

0 comments1 min readEA link

Conflicts between emotional schemas often involve internal coercion

richard_ngo17 May 2023 10:08 UTC

34 points

0 comments1 min readEA link

We learn long-lasting strategies to protect ourselves from danger and rejection

richard_ngo16 May 2023 16:36 UTC

43 points

0 comments1 min readEA link

Judgments often smuggle in implicit standards

richard_ngo15 May 2023 18:50 UTC

46 points

1 comment1 min readEA link

From fear to excitement

richard_ngo15 May 2023 6:23 UTC

62 points

1 comment1 min readEA link

Clarifying and predicting AGI

richard_ngo4 May 2023 15:56 UTC

69 points

2 comments1 min readEA link

AGI safety career advice

richard_ngo2 May 2023 7:36 UTC

211 points

20 comments1 min readEA link

AGISF adaptation for in-person groups

Sam Marks17 Jan 2023 18:33 UTC

30 points

0 comments3 min readEA link

(www.lesswrong.com)

Applications open for AGI Safety Fundamentals: Alignment Course

Jamie B13 Dec 2022 10:50 UTC

75 points

0 comments2 min readEA link

Brainstorming ways to make EA safer and more inclusive

richard_ngo15 Nov 2022 11:14 UTC

149 points

97 comments1 min readEA link