Lukas Finnveden

Karma: 2,449

Previously “Lanrian” on here. Research analyst at Open Philanthropy. Views are my own.

AI-enabled coups: a small group could use AI to seize power

Tom Davidson, Lukas Finnveden and rosehadshar

Apr 16, 2025, 4:51 PM

128 points

18 comments7 min readLW link

What’s important in “AI for epistemics”?

Lukas FinnvedenAug 24, 2024, 1:27 AM

48 points

0 comments28 min readLW link

(www.forethought.org)

Project ideas: Backup plans & Cooperative AI

Lukas FinnvedenJan 8, 2024, 5:19 PM

18 points

0 comments LW link

(www.forethought.org)

Project ideas: Sentience and rights of digital minds

Lukas FinnvedenJan 7, 2024, 5:34 PM

20 points

0 comments LW link

(www.forethought.org)

Project ideas: Epistemics

Lukas FinnvedenJan 5, 2024, 11:41 PM

43 points

4 comments LW link

(www.forethought.org)

Project ideas: Governance during explosive technological growth

Lukas FinnvedenJan 4, 2024, 11:51 PM

14 points

0 comments LW link

(www.forethought.org)

Non-alignment project ideas for making transformative AI go well

Lukas FinnvedenJan 4, 2024, 7:23 AM

44 points

1 comment LW link

(www.forethought.org)

Memo on some neglected topics

Lukas FinnvedenNov 11, 2023, 2:01 AM

28 points

2 comments LW link

(open.substack.com)

Implications of evidential cooperation in large worlds

Lukas FinnvedenAug 23, 2023, 12:43 AM

39 points

4 comments17 min readLW link

(lukasfinnveden.substack.com)

PaLM-2 & GPT-4 in “Extrapolating GPT-N performance”

Lukas FinnvedenMay 30, 2023, 6:33 PM

57 points

6 comments6 min readLW link

Some thoughts on automating alignment research

Lukas FinnvedenMay 26, 2023, 1:50 AM

30 points

4 comments6 min readLW link

Before smart AI, there will be many mediocre or specialized AIs

Lukas FinnvedenMay 26, 2023, 1:38 AM

58 points

14 comments9 min readLW link 1 review

PaLM in “Extrapolating GPT-N performance”

Lukas FinnvedenApr 6, 2022, 1:05 PM

85 points

19 comments2 min readLW link

Truthful AI: Developing and governing AI that does not lie

Owain_Evans, owencb and Lukas Finnveden

Oct 18, 2021, 6:37 PM

82 points

9 comments10 min readLW link

OpenAI: “Scaling Laws for Transfer”, Hernandez et al.

Lukas FinnvedenFeb 4, 2021, 12:49 PM

14 points

3 comments1 min readLW link

(arxiv.org)

Prediction can be Outer Aligned at Optimum

Lukas FinnvedenJan 10, 2021, 6:48 PM

15 points

12 comments11 min readLW link

Extrapolating GPT-N performance

Lukas FinnvedenDec 18, 2020, 9:41 PM

112 points

31 comments22 min readLW link 1 review

Formalising decision theory is hard

Lukas FinnvedenAug 23, 2019, 3:27 AM

17 points

19 comments2 min readLW link

Quantifying anthropic effects on the Fermi paradox

Lukas FinnvedenFeb 15, 2019, 10:51 AM

29 points

5 comments27 min readLW link