technicalities

Karma: 1,026

The jailbreak argument against LLM values

technicalities10 Nov 2025 12:05 UTC

24 points

2 comments6 min readLW link

curate

technicalities14 Jan 2025 14:40 UTC

12 points

0 comments2 min readLW link

Shallow review of technical AI safety, 2024

technicalities, Stag, Stephen McAleese, jordine and Dr. David Mathers

29 Dec 2024 12:01 UTC

197 points

35 comments41 min readLW link

“Safety as a Scientific Pursuit” (2024)

technicalities23 Jan 2024 12:40 UTC

17 points

3 comments2 min readLW link

(banburismus.substack.com)

Appendices to the live agendas

technicalities and Stag

27 Nov 2023 11:10 UTC

16 points

4 comments1 min readLW link

Shallow review of live agendas in alignment & safety

technicalities and Stag

27 Nov 2023 11:10 UTC

349 points

73 comments29 min readLW link 1 review

ActAdd: Steering Language Models without Optimization

technicalities, TurnTrout, lisathiergart, David Udell, Ulisse Mini and Monte M

6 Sep 2023 17:21 UTC

105 points

3 comments2 min readLW link

(arxiv.org)

Announcing the Alignment of Complex Systems Research Group

Jan_Kulveit and technicalities

4 Jun 2022 4:10 UTC

92 points

20 comments5 min readLW link

Case for emergency response teams

Jan_Kulveit and technicalities

5 Apr 2022 12:45 UTC

24 points

0 comments5 min readLW link

(forum.effectivealtruism.org)

Hinges and crises

Jan_Kulveit and technicalities

29 Mar 2022 11:11 UTC

44 points

7 comments3 min readLW link

(forum.effectivealtruism.org)

Experimental longtermism: theory needs data

Jan_Kulveit and technicalities

24 Mar 2022 8:23 UTC

52 points

0 comments4 min readLW link

(forum.effectivealtruism.org)

We have some evidence that masks work

technicalities11 Jul 2021 18:36 UTC

97 points

13 comments5 min readLW link

Self-help, hard and soft

technicalities7 Jun 2020 15:39 UTC

16 points

0 comments2 min readLW link

Automatic for the people

technicalities8 Jul 2018 14:23 UTC

18 points

23 comments7 min readLW link