RSS

Lukas Finnveden

Karma: 2,093

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

Pro­ject ideas: Backup plans & Co­op­er­a­tive AI

Lukas Finnveden8 Jan 2024 17:19 UTC
17 points
0 comments1 min readLW link
(lukasfinnveden.substack.com)

Pro­ject ideas: Sen­tience and rights of digi­tal minds

Lukas Finnveden7 Jan 2024 17:34 UTC
20 points
0 comments1 min readLW link
(lukasfinnveden.substack.com)

Pro­ject ideas: Epistemics

Lukas Finnveden5 Jan 2024 23:41 UTC
41 points
4 comments1 min readLW link
(lukasfinnveden.substack.com)

Pro­ject ideas: Gover­nance dur­ing ex­plo­sive tech­nolog­i­cal growth

Lukas Finnveden4 Jan 2024 23:51 UTC
13 points
0 comments1 min readLW link
(lukasfinnveden.substack.com)

Non-al­ign­ment pro­ject ideas for mak­ing trans­for­ma­tive AI go well

Lukas Finnveden4 Jan 2024 7:23 UTC
35 points
1 comment1 min readLW link
(lukasfinnveden.substack.com)

Memo on some ne­glected topics

Lukas Finnveden11 Nov 2023 2:01 UTC
28 points
2 comments1 min readLW link
(open.substack.com)

Im­pli­ca­tions of ev­i­den­tial co­op­er­a­tion in large worlds

Lukas Finnveden23 Aug 2023 0:43 UTC
39 points
4 comments17 min readLW link
(lukasfinnveden.substack.com)

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

Lukas Finnveden30 May 2023 18:33 UTC
55 points
6 comments6 min readLW link

Some thoughts on au­tomat­ing al­ign­ment research

Lukas Finnveden26 May 2023 1:50 UTC
30 points
4 comments6 min readLW link

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

Lukas Finnveden26 May 2023 1:38 UTC
47 points
4 comments9 min readLW link

PaLM in “Ex­trap­o­lat­ing GPT-N perfor­mance”

Lukas Finnveden6 Apr 2022 13:05 UTC
83 points
19 comments2 min readLW link

Truth­ful AI: Devel­op­ing and gov­ern­ing AI that does not lie

Owain_Evans, owencb and Lukas Finnveden
18 Oct 2021 18:37 UTC
81 points
9 comments10 min readLW link

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

Lukas Finnveden4 Feb 2021 12:49 UTC
13 points
3 comments1 min readLW link
(arxiv.org)

Pre­dic­tion can be Outer Aligned at Optimum

Lukas Finnveden10 Jan 2021 18:48 UTC
15 points
12 comments11 min readLW link

Ex­trap­o­lat­ing GPT-N performance

Lukas Finnveden18 Dec 2020 21:41 UTC
108 points
31 comments22 min readLW link1 review

For­mal­is­ing de­ci­sion the­ory is hard

Lukas Finnveden23 Aug 2019 3:27 UTC
17 points
19 comments2 min readLW link

Quan­tify­ing an­thropic effects on the Fermi paradox

Lukas Finnveden15 Feb 2019 10:51 UTC
26 points
5 comments41 min readLW link