RSS

Open Problems

TagLast edit: 18 Aug 2021 14:54 UTC by plex

Open problems(or open questions) are the things in a field that haven’t yet been figured out. Gathering them all in the same place can help to see on what’s the frontier of that field or find things to work on.

See also Hamming Questions

[Question] What are the open prob­lems in Hu­man Ra­tion­al­ity?

Raemon13 Jan 2019 4:46 UTC
99 points
93 comments1 min readLW link3 reviews

[Question] Prob­lems In­volv­ing Ab­strac­tion?

johnswentworth20 Oct 2020 16:49 UTC
30 points
12 comments1 min readLW link

Open Prob­lems in AI X-Risk [PAIS #5]

10 Jun 2022 2:08 UTC
61 points
6 comments36 min readLW link

A Re­quest for Open Problems

MrHen8 May 2009 13:33 UTC
28 points
103 comments1 min readLW link

200 Con­crete Open Prob­lems in Mechanis­tic In­ter­pretabil­ity: Introduction

Neel Nanda28 Dec 2022 21:06 UTC
106 points
0 comments10 min readLW link

Why Are Max­i­mum En­tropy Distri­bu­tions So Ubiquitous?

johnswentworth5 Apr 2023 20:12 UTC
68 points
6 comments9 min readLW link

A Primer On Chaos

johnswentworth28 Mar 2023 18:01 UTC
53 points
9 comments9 min readLW link

[Question] What‘s in your list of un­solved prob­lems in AI al­ign­ment?

jacquesthibs7 Mar 2023 18:58 UTC
60 points
9 comments1 min readLW link

UDT shows that de­ci­sion the­ory is more puz­zling than ever

Wei Dai13 Sep 2023 12:26 UTC
198 points
55 comments1 min readLW link

Con­crete em­piri­cal re­search pro­jects in mechanis­tic anomaly detection

3 Apr 2024 23:07 UTC
43 points
2 comments10 min readLW link

Open Prob­lems in Nega­tive Side Effect Minimization

6 May 2022 9:37 UTC
12 points
6 comments17 min readLW link

Con­di­tion­ing Pre­dic­tive Models: Open prob­lems, Con­clu­sion, and Appendix

10 Feb 2023 19:21 UTC
36 points
3 comments11 min readLW link

Ro­bust Agency for Peo­ple and Organizations

Raemon19 Jul 2019 1:18 UTC
60 points
10 comments12 min readLW link

Deep For­get­ting & Un­learn­ing for Safely-Scoped LLMs

scasper5 Dec 2023 16:48 UTC
120 points
29 comments13 min readLW link

Open prob­lems in ac­ti­va­tion engineering

24 Jul 2023 19:46 UTC
51 points
2 comments1 min readLW link
(coda.io)

Open Prob­lems with Myopia

10 Mar 2021 18:38 UTC
66 points
16 comments8 min readLW link

[Question] Open prob­lem: how can we quan­tify player al­ign­ment in 2x2 nor­mal-form games?

TurnTrout16 Jun 2021 2:09 UTC
23 points
59 comments1 min readLW link

A Cer­tain For­mal­iza­tion of Cor­rigi­bil­ity Is VNM-Incoherent

TurnTrout20 Nov 2021 0:30 UTC
67 points
24 comments8 min readLW link

[In­tro to brain-like-AGI safety] 15. Con­clu­sion: Open prob­lems, how to help, AMA

Steven Byrnes17 May 2022 15:11 UTC
92 points
10 comments15 min readLW link

Open tech­ni­cal prob­lem: A Quinean proof of Löb’s the­o­rem, for an eas­ier car­toon guide

Andrew_Critch24 Nov 2022 21:16 UTC
58 points
35 comments3 min readLW link1 review

200 COP in MI: Study­ing Learned Fea­tures in Lan­guage Models

Neel Nanda19 Jan 2023 3:48 UTC
24 points
2 comments30 min readLW link

Open Prob­lems Re­lated to Solomonoff Induction

Wei Dai6 Jun 2012 0:26 UTC
44 points
104 comments2 min readLW link

Pro­posal for “Open Prob­lems in Friendly AI”

lukeprog1 Jun 2012 2:06 UTC
33 points
14 comments1 min readLW link

Tiling Agents for Self-Mod­ify­ing AI (OPFAI #2)

Eliezer Yudkowsky6 Jun 2013 20:24 UTC
88 points
259 comments3 min readLW link

AI Safety De­bate and Its Applications

VojtaKovarik23 Jul 2019 22:31 UTC
38 points
5 comments11 min readLW link

An an­gle of at­tack on Open Prob­lem #1

Benya18 Aug 2012 12:08 UTC
48 points
85 comments7 min readLW link

Friendly AI Re­search and Taskification

multifoliaterose14 Dec 2010 6:30 UTC
30 points
47 comments5 min readLW link

The­ory 1–4

Arilwen Oriloth22 May 2024 16:08 UTC
1 point
0 comments1 min readLW link

Se­cret Col­lu­sion: Will We Know When to Un­plug AI?

16 Sep 2024 16:07 UTC
55 points
7 comments31 min readLW link

Two Blegs

talisman26 Mar 2009 4:42 UTC
4 points
5 comments1 min readLW link

Open Prob­lems Create Paradigms

johnswentworth9 Nov 2020 20:04 UTC
50 points
5 comments2 min readLW link

Towards Hodge-podge Alignment

Cleo Nardo19 Dec 2022 20:12 UTC
93 points
30 comments9 min readLW link

[Question] What ques­tion would you like to col­lab­o­rate on?

weathersystems2 Jun 2021 19:31 UTC
12 points
12 comments2 min readLW link

Hal­loween Problem

Saint Blasphemer24 Oct 2023 16:46 UTC
−10 points
1 comment1 min readLW link

Pre­serv­ing our her­i­tage: Build­ing a move­ment and a knowl­edge ark for cur­rent and fu­ture generations

rnk829 Nov 2023 19:20 UTC
0 points
5 comments12 min readLW link

Lay­ing the Foun­da­tions for Vi­sion and Mul­ti­modal Mechanis­tic In­ter­pretabil­ity & Open Problems

13 Mar 2024 17:09 UTC
43 points
13 comments14 min readLW link

Open ques­tion: are min­i­mal cir­cuits dae­mon-free?

paulfchristiano5 May 2018 22:40 UTC
83 points
70 comments2 min readLW link1 review

[LINK] The most im­por­tant un­solved prob­lems in ethics

jefftk17 Oct 2012 20:03 UTC
35 points
46 comments1 min readLW link

Open Prob­lems in Archipelago

Raemon16 Apr 2019 22:57 UTC
44 points
14 comments3 min readLW link

Open Prob­lems Re­lated to the Sin­gu­lar­ity (draft 1)

lukeprog13 Dec 2011 10:57 UTC
53 points
42 comments4 min readLW link

Open Problems

lukeprog5 Jul 2011 7:25 UTC
41 points
11 comments2 min readLW link
No comments.