Ramana Kumar

Karma: 1,455

Dialogue on What It Means For Something to Have A Function/Purpose

johnswentworth, Ramana Kumar and Steve Petersen

15 Jul 2024 16:28 UTC

38 points

5 comments16 min readLW link

Consent across power differentials

Ramana Kumar9 Jul 2024 11:42 UTC

50 points

12 comments3 min readLW link

Refining the Sharp Left Turn threat model, part 2: applying alignment techniques

Vika, Vikrant Varma, Ramana Kumar and Rohin Shah

25 Nov 2022 14:36 UTC

39 points

9 comments6 min readLW link

(vkrakovna.wordpress.com)

Threat Model Literature Review

zac_kenton, Rohin Shah, David Lindner, Vikrant Varma, Vika, Mary Phuong, Ramana Kumar and Elliot Catt

1 Nov 2022 11:03 UTC

77 points

4 comments25 min readLW link

Clarifying AI X-risk

zac_kenton, Rohin Shah, David Lindner, Vikrant Varma, Vika, Mary Phuong, Ramana Kumar and Elliot Catt

1 Nov 2022 11:03 UTC

127 points

24 comments4 min readLW link 1 review

Autonomy as taking responsibility for reference maintenance

Ramana Kumar17 Aug 2022 12:50 UTC

56 points

3 comments5 min readLW link

Refining the Sharp Left Turn threat model, part 1: claims and mechanisms

Vika, Vikrant Varma, Ramana Kumar and Mary Phuong

12 Aug 2022 15:17 UTC

86 points

4 comments3 min readLW link 1 review

(vkrakovna.wordpress.com)

Will Capabilities Generalise More?

Ramana Kumar29 Jun 2022 17:12 UTC

132 points

39 comments4 min readLW link

ELK contest submission: route understanding through the human ontology

Vika, Ramana Kumar and Vikrant Varma

14 Mar 2022 21:42 UTC

21 points

2 comments2 min readLW link

P₂B: Plan to P₂B Better

Ramana Kumar and Daniel Kokotajlo

24 Oct 2021 15:21 UTC

38 points

17 comments6 min readLW link

Optimization Concepts in the Game of Life

Vika and Ramana Kumar

16 Oct 2021 20:51 UTC

75 points

16 comments10 min readLW link

Intelligence or Evolution?

Ramana Kumar9 Oct 2021 17:14 UTC

54 points

15 comments3 min readLW link

Draft papers for REALab and Decoupled Approval on tampering

Jonathan Uesato and Ramana Kumar

28 Oct 2020 16:01 UTC

47 points

2 comments1 min readLW link

Modeling AGI Safety Frameworks with Causal Influence Diagrams

Ramana Kumar21 Jun 2019 12:50 UTC

43 points

6 comments1 min readLW link

(arxiv.org)

Thoughts on Human Models

Ramana Kumar and Scott Garrabrant

21 Feb 2019 9:10 UTC

126 points

32 comments10 min readLW link 1 review

Cambridge UK Meetup Saturday 12 February

Ramana Kumar2 Feb 2011 14:20 UTC

9 points

22 comments1 min readLW link