Jan_Kulveit

Karma: 4,932

Studying behaviour and interactions of boundedly rational agents, AI alignment and complex systems.

Research fellow at Future of Humanity Institute, Oxford. Other projects: European Summer Program on Rationality. Human-aligned AI Summer School. Epistea Lab.

ACS is hiring: why work here and why not

Jan_Kulveit23 Oct 2025 9:38 UTC

39 points

4 comments2 min readEA link

Do Not Tile the Lightcone with Your Confused Ontology

Jan_Kulveit13 Jun 2025 12:45 UTC

45 points

4 comments5 min readEA link

(boundedlyrational.substack.com)

Apply now to Human-aligned AI Summer School 2025

Pivocajs6 Jun 2025 19:34 UTC

8 points

1 comment2 min readEA link

Gradual Disempowerment: Systemic Existential Risks from Incremental AI Development

Jan_Kulveit30 Jan 2025 17:07 UTC

45 points

4 comments2 min readEA link

(gradual-disempowerment.ai)

“Charity” as a conflationary alliance term

Jan_Kulveit13 Dec 2024 7:53 UTC

76 points

4 comments5 min readEA link

(www.lesswrong.com)

Jan_Kulveit’s Quick takes

Jan_Kulveit12 Dec 2024 22:22 UTC

7 points

9 comments EA link

Distancing EA from rationality is foolish

Jan_Kulveit25 Jun 2024 21:02 UTC

135 points

33 comments2 min readEA link

Announcing Human-aligned AI Summer School

Jan_Kulveit22 May 2024 8:55 UTC

33 points

0 comments1 min readEA link

(humanaligned.ai)

Box inversion revisited

Jan_Kulveit7 Nov 2023 11:09 UTC

22 points

1 comment8 min readEA link

We don’t understand what happened with culture enough

Jan_Kulveit9 Oct 2023 14:56 UTC

29 points

2 comments6 min readEA link

Talking publicly about AI risk

Jan_Kulveit24 Apr 2023 9:19 UTC

152 points

13 comments6 min readEA link

Why Simulator AIs want to be Active Inference AIs

Jan_Kulveit11 Apr 2023 9:06 UTC

22 points

0 comments8 min readEA link

(www.lesswrong.com)

The space of systems and the space of maps

Jan_Kulveit22 Mar 2023 16:05 UTC

12 points

0 comments5 min readEA link

(www.lesswrong.com)

Cyborg Periods: There will be multiple AI transitions

Jan_Kulveit22 Feb 2023 16:09 UTC

68 points

1 comment6 min readEA link

Deontology and virtue ethics as “effective theories” of consequentialist ethics

Jan_Kulveit17 Nov 2022 9:20 UTC

57 points

12 comments10 min readEA link

We can do better than argmax

Jan_Kulveit10 Oct 2022 10:32 UTC

113 points

36 comments10 min readEA link

Limits to Legibility

Jan_Kulveit29 Jun 2022 17:45 UTC

106 points

3 comments5 min readEA link

(www.lesswrong.com)

Ways money can make things worse

Jan_Kulveit21 Jun 2022 15:26 UTC

167 points

3 comments9 min readEA link

Continuity Assumptions

Jan_Kulveit13 Jun 2022 21:36 UTC

44 points

4 comments4 min readEA link

(www.alignmentforum.org)

Different forms of capital

Jan_Kulveit25 Apr 2022 8:05 UTC

101 points

8 comments2 min readEA link