RSS

SoerenMind

Karma: 1,181

How to Catch an AI Liar: Lie De­tec­tion in Black-Box LLMs by Ask­ing Un­re­lated Questions

JanB, Owain_Evans and SoerenMind
28 Sep 2023 18:53 UTC
187 points
39 comments3 min readLW link1 review

Wikipe­dia as an in­tro­duc­tion to the al­ign­ment problem

SoerenMind29 May 2023 18:43 UTC
83 points
10 comments1 min readLW link
(en.wikipedia.org)

The Align­ment Prob­lem from a Deep Learn­ing Per­spec­tive (ma­jor rewrite)

SoerenMind, Richard_Ngo and LawrenceC
10 Jan 2023 16:06 UTC
84 points
8 comments39 min readLW link
(arxiv.org)

[Question] How much to op­ti­mize for the short-timelines sce­nario?

SoerenMind21 Jul 2022 10:47 UTC
20 points
3 comments1 min readLW link

In­fer­ence cost limits the im­pact of ever larger models

SoerenMind23 Oct 2021 10:51 UTC
42 points
29 comments2 min readLW link

So­erenMind’s Shortform

SoerenMind11 Jun 2021 20:19 UTC
5 points
2 comments1 min readLW link

FHI pa­per pub­lished in Science: in­ter­ven­tions against COVID-19

SoerenMind16 Dec 2020 21:19 UTC
119 points
0 comments3 min readLW link

How to do re­mote co-working

SoerenMind8 May 2020 19:38 UTC
25 points
11 comments1 min readLW link

[Question] How im­por­tant are model sizes to your timeline pre­dic­tions?

SoerenMind5 Sep 2019 17:34 UTC
11 points
1 comment1 min readLW link

[Question] What are some good ex­am­ples of gam­ing that is hard to de­tect?

SoerenMind16 May 2019 16:10 UTC
5 points
3 comments1 min readLW link

[Question] Any re­but­tals of Chris­ti­ano and AI Im­pacts on take­off speeds?

SoerenMind21 Apr 2019 20:39 UTC
67 points
26 comments1 min readLW link

Some in­tu­ition on why con­scious­ness seems subjective

SoerenMind27 Jul 2018 22:37 UTC
20 points
10 comments7 min readLW link

Up­dat­ing to­wards the simu­la­tion hy­poth­e­sis be­cause you think about AI

SoerenMind5 Mar 2016 22:23 UTC
11 points
21 comments3 min readLW link

Work­ing at MIRI: An in­ter­view with Malo Bourgon

SoerenMind1 Nov 2015 12:54 UTC
13 points
2 comments4 min readLW link

Meetup : ‘The Most Good Good You Can Do’ (Effec­tive Altru­ism meetup)

SoerenMind14 May 2015 18:32 UTC
2 points
0 comments1 min readLW link

Meetup : Utrecht- Brain­storm and ethics dis­cus­sion at the Film Café

SoerenMind19 May 2014 20:49 UTC
2 points
2 comments1 min readLW link

Meetup : Utrecht—So­cial dis­cus­sion at the Film Café

SoerenMind12 May 2014 13:10 UTC
2 points
0 comments1 min readLW link

Meetup : Utrecht

SoerenMind20 Apr 2014 10:14 UTC
3 points
2 comments1 min readLW link

Meetup : Utrecht: Be­havi­oural eco­nomics, game the­ory...

SoerenMind7 Apr 2014 13:54 UTC
5 points
1 comment1 min readLW link

Meetup : Utrecht: More on effec­tive altruism

SoerenMind27 Mar 2014 0:40 UTC
3 points
3 comments1 min readLW link