RSS

Remmelt

Karma: 459

Research Coordinator of area “Do Not Build Uncontrollable AI” for AI Safety Camp.

See explainer on why AGI could not be controlled enough to stay safe:
https://​​www.lesswrong.com/​​posts/​​xp6n2MG5vQkPpFEBH/​​the-control-problem-unsolved-or-unsolvable

This might be the last AI Safety Camp

Remmelt and Linda Linsefors
24 Jan 2024 9:33 UTC
181 points
33 comments1 min readLW link

Fund­ing case: AI Safety Camp

Remmelt and Linda Linsefors
12 Dec 2023 9:08 UTC
65 points
5 comments5 min readLW link
(manifund.org)

The Con­trol Prob­lem: Un­solved or Un­solv­able?

Remmelt2 Jun 2023 15:42 UTC
49 points
46 comments14 min readLW link

The first AI Safety Camp & onwards

Remmelt7 Jun 2018 20:13 UTC
46 points
0 comments8 min readLW link

Some blindspots in ra­tio­nal­ity and effec­tive altruism

Remmelt19 Mar 2021 11:40 UTC
37 points
44 comments14 min readLW link

Thir­teen Law­suits against OpenAI

Remmelt9 Mar 2024 12:22 UTC
31 points
4 comments1 min readLW link

The Values-to-Ac­tions De­ci­sion Chain

Remmelt30 Jun 2018 21:52 UTC
29 points
6 comments10 min readLW link

How teams went about their re­search at AI Safety Camp edi­tion 8

Remmelt, Linda Linsefors and Kristi Uustalu
9 Sep 2023 16:34 UTC
28 points
0 comments13 min readLW link

Why I think it’s net harm­ful to do tech­ni­cal safety re­search at AGI labs

Remmelt7 Feb 2024 4:17 UTC
26 points
24 comments1 min readLW link

How teams went about their re­search at AI Safety Camp edi­tion 5

Remmelt28 Jun 2021 15:15 UTC
24 points
0 comments6 min readLW link

My first con­ver­sa­tion with An­nie Altman

Remmelt21 Nov 2023 21:58 UTC
8 points
3 comments1 min readLW link
(open.spotify.com)

Del­e­gated agents in prac­tice: How com­pa­nies might end up sel­l­ing AI ser­vices that act on be­half of con­sumers and coal­i­tions, and what this im­plies for safety research

Remmelt26 Nov 2020 11:17 UTC
7 points
3 comments4 min readLW link

List #1: Why stop­ping the de­vel­op­ment of AGI is hard but doable

Remmelt24 Dec 2022 9:52 UTC
6 points
11 comments5 min readLW link

In­sti­tu­tions Can­not Res­train Dark-Triad AI Exploitation

Remmelt and flandry19
27 Dec 2022 10:34 UTC
5 points
0 comments5 min readLW link
(mflb.com)

A parable of brightspots and blindspots

Remmelt21 Mar 2021 18:18 UTC
4 points
0 comments3 min readLW link

List #3: Why not to as­sume on prior that AGI-al­ign­ment workarounds are available

Remmelt24 Dec 2022 9:54 UTC
4 points
1 comment3 min readLW link

[Question] What did AI Safety’s spe­cific fund­ing of AGI R&D labs lead to?

Remmelt5 Jul 2023 15:51 UTC
3 points
0 comments1 min readLW link

The con­ver­gent dy­namic we missed

Remmelt12 Dec 2023 23:19 UTC
2 points
2 comments1 min readLW link

In­tro­duc­tion: Bias in Eval­u­at­ing AGI X-Risks

Remmelt and flandry19
27 Dec 2022 10:27 UTC
1 point
0 comments3 min readLW link

An­chor­ing fo­cal­ism and the Iden­ti­fi­able vic­tim effect: Bias in Eval­u­at­ing AGI X-Risks

Remmelt7 Jan 2023 9:59 UTC
1 point
2 comments1 min readLW link