Raymond Douglas

Karma: 1,511

Summary of our Workshop on Post-AGI Outcomes

David Duvenaud, Raymond Douglas, Nora_Ammann and Jan_Kulveit

29 Aug 2025 17:14 UTC

94 points

3 comments3 min readLW link

Healthy AI relationships as a microcosm

Raymond Douglas23 Jul 2025 15:59 UTC

13 points

0 comments2 min readLW link

‘AI for societal uplift’ as a path to victory

Raymond Douglas4 Jul 2025 15:32 UTC

85 points

22 comments2 min readLW link

Upcoming workshop on Post-AGI Civilizational Equilibria

David Duvenaud, Jan_Kulveit, Raymond Douglas, Nora_Ammann and David Scott Krueger (formerly: capybaralet)

21 Jun 2025 15:57 UTC

25 points

0 comments1 min readLW link

Gradual Disempowerment: Concrete Research Projects

Raymond Douglas29 May 2025 18:55 UTC

99 points

10 comments10 min readLW link

Disempowerment spirals as a likely mechanism for existential catastrophe

Raymond Douglas and owencb

10 Apr 2025 14:37 UTC

74 points

7 comments5 min readLW link

Selection Pressures on LM Personas

Raymond Douglas28 Mar 2025 20:33 UTC

30 points

0 comments3 min readLW link

Gradual Disempowerment: Systemic Existential Risks from Incremental AI Development

Jan_Kulveit, Raymond Douglas, Nora_Ammann, Deger Turan, David Scott Krueger (formerly: capybaralet) and David Duvenaud

30 Jan 2025 17:03 UTC

166 points

65 comments2 min readLW link

(gradual-disempowerment.ai)

What does success look like?

Raymond Douglas23 Jan 2025 17:48 UTC

11 points

0 comments3 min readLW link

The Choice Transition

owencb and Raymond Douglas

18 Nov 2024 12:30 UTC

53 points

4 comments15 min readLW link

(strangecities.substack.com)

Decomposing Agency — capabilities without desires

owencb and Raymond Douglas

11 Jul 2024 9:38 UTC

153 points

32 comments12 min readLW link

(strangecities.substack.com)

ChatGPT can learn indirect control

Raymond Douglas21 Mar 2024 21:11 UTC

213 points

27 comments1 min readLW link

Predictive model agents are sort of corrigible

Raymond Douglas5 Jan 2024 14:05 UTC

35 points

6 comments3 min readLW link

Picking Mentors For Research Programmes

Raymond Douglas10 Nov 2023 13:01 UTC

105 points

8 comments4 min readLW link

Goal-Direction for Simulated Agents

Raymond Douglas12 Jul 2023 17:06 UTC

33 points

2 comments6 min readLW link

Language Models can be Utility-Maximising Agents

Raymond Douglas1 Feb 2023 18:13 UTC

22 points

1 comment2 min readLW link

Taking Clones Seriously

Raymond Douglas1 Dec 2021 17:29 UTC

56 points

45 comments2 min readLW link

Why Save The Drowning Child: Ethics Vs Theory

Raymond Douglas16 Nov 2021 19:07 UTC

17 points

12 comments4 min readLW link

The Opt-Out Clause

Raymond Douglas3 Nov 2021 22:02 UTC

39 points

49 comments1 min readLW link

30-ish focusing tips

Raymond Douglas22 Oct 2021 19:38 UTC

22 points

4 comments6 min readLW link