Archive
Sequences
About
Search
Log In
Questions
Events
Shortform
Alignment Forum
AF Comments
Home
Featured
All
Tags
Recent
Comments
RSS
Lukas Finnveden
Karma:
2,094
Previously “Lanrian” on here. Research analyst at Open Philanthropy. Views are my own.
All
Posts
Comments
New
Top
Old
Extrapolating GPT-N performance
Lukas Finnveden
18 Dec 2020 21:41 UTC
108
points
31
comments
22
min read
LW
link
1
review
PaLM in “Extrapolating GPT-N performance”
Lukas Finnveden
6 Apr 2022 13:05 UTC
83
points
19
comments
2
min read
LW
link
PaLM-2 & GPT-4 in “Extrapolating GPT-N performance”
Lukas Finnveden
30 May 2023 18:33 UTC
55
points
6
comments
6
min read
LW
link
Before smart AI, there will be many mediocre or specialized AIs
Lukas Finnveden
26 May 2023 1:38 UTC
51
points
4
comments
9
min read
LW
link
Project ideas: Epistemics
Lukas Finnveden
5 Jan 2024 23:41 UTC
41
points
4
comments
1
min read
LW
link
(lukasfinnveden.substack.com)
Implications of evidential cooperation in large worlds
Lukas Finnveden
23 Aug 2023 0:43 UTC
39
points
4
comments
17
min read
LW
link
(lukasfinnveden.substack.com)
Non-alignment project ideas for making transformative AI go well
Lukas Finnveden
4 Jan 2024 7:23 UTC
35
points
1
comment
1
min read
LW
link
(lukasfinnveden.substack.com)
Some thoughts on automating alignment research
Lukas Finnveden
26 May 2023 1:50 UTC
30
points
4
comments
6
min read
LW
link
Memo on some neglected topics
Lukas Finnveden
11 Nov 2023 2:01 UTC
28
points
2
comments
1
min read
LW
link
(open.substack.com)
Quantifying anthropic effects on the Fermi paradox
Lukas Finnveden
15 Feb 2019 10:51 UTC
26
points
5
comments
41
min read
LW
link
Project ideas: Sentience and rights of digital minds
Lukas Finnveden
7 Jan 2024 17:34 UTC
20
points
0
comments
1
min read
LW
link
(lukasfinnveden.substack.com)
Project ideas: Backup plans & Cooperative AI
Lukas Finnveden
8 Jan 2024 17:19 UTC
17
points
0
comments
1
min read
LW
link
(lukasfinnveden.substack.com)
Formalising decision theory is hard
Lukas Finnveden
23 Aug 2019 3:27 UTC
17
points
19
comments
2
min read
LW
link
Prediction can be Outer Aligned at Optimum
Lukas Finnveden
10 Jan 2021 18:48 UTC
15
points
12
comments
11
min read
LW
link
OpenAI: “Scaling Laws for Transfer”, Hernandez et al.
Lukas Finnveden
4 Feb 2021 12:49 UTC
13
points
3
comments
1
min read
LW
link
(arxiv.org)
Project ideas: Governance during explosive technological growth
Lukas Finnveden
4 Jan 2024 23:51 UTC
13
points
0
comments
1
min read
LW
link
(lukasfinnveden.substack.com)
Back to top