RSS

Con­crete benefits of mak­ing predictions

17 Oct 2024 14:23 UTC
26 points
2 comments6 min readLW link
(fatebook.io)

Arith­metic is an un­der­rated world-mod­el­ing technology

dynomight17 Oct 2024 14:00 UTC
43 points
3 comments6 min readLW link
(dynomight.net)

The Com­pu­ta­tional Com­plex­ity of Cir­cuit Dis­cov­ery for In­ner Interpretability

Bogdan Ionut Cirstea17 Oct 2024 13:18 UTC
9 points
0 comments1 min readLW link
(arxiv.org)

[Question] Is there a known method to find oth­ers who came across the same po­ten­tial in­fo­haz­ard with­out spoiling it to the pub­lic?

hive17 Oct 2024 10:47 UTC
−3 points
5 comments1 min readLW link

It is time to start war gam­ing for AGI

yanni kyriacos17 Oct 2024 5:14 UTC
4 points
1 comment1 min readLW link

[Question] Re­in­force­ment Learn­ing: Essen­tial Step Towards AGI or Ir­rele­vant?

Double17 Oct 2024 3:37 UTC
1 point
0 comments1 min readLW link

[Question] En­deav­orOTC le­git?

FinalFormal217 Oct 2024 1:33 UTC
−4 points
0 comments1 min readLW link

Bit­ter les­sons about lu­cid dreaming

avturchin16 Oct 2024 21:27 UTC
64 points
26 comments2 min readLW link

Towards Quan­ti­ta­tive AI Risk Management

16 Oct 2024 19:26 UTC
27 points
1 comment6 min readLW link

Why hu­mans won’t con­trol su­per­hu­man AIs.

Spiritus Dei16 Oct 2024 16:48 UTC
−11 points
1 comment6 min readLW link

Against em­pa­thy-by-default

Steven Byrnes16 Oct 2024 16:38 UTC
53 points
10 comments7 min readLW link

can­cer rates af­ter gene therapy

bhauth16 Oct 2024 15:32 UTC
34 points
0 comments3 min readLW link
(bhauth.com)

[Question] Change My Mind: Thirders in “Sleep­ing Beauty” are Just Do­ing Episte­mol­ogy Wrong

DragonGod16 Oct 2024 10:20 UTC
7 points
50 comments6 min readLW link

[Question] After up­load­ing your con­scious­ness...

Jinge Wang16 Oct 2024 3:52 UTC
−2 points
0 comments1 min readLW link

The ELYSIUM Pro­posal - Ex­trap­o­lated voLi­tions Yield­ing Separate In­di­vi­d­u­al­ized Utopias for Mankind

Roko16 Oct 2024 1:24 UTC
1 point
6 comments1 min readLW link
(transhumanaxiology.substack.com)

Distil­la­tion Of Deep­Seek-Prover V1.5

IvanLin15 Oct 2024 18:53 UTC
1 point
1 comment3 min readLW link

Im­prov­ing Model-Writ­ten Evals for AI Safety Benchmarking

15 Oct 2024 18:25 UTC
20 points
0 comments18 min readLW link

Tak­ing non­log­i­cal con­cepts seriously

Kris Brown15 Oct 2024 18:16 UTC
7 points
2 comments18 min readLW link
(topos.site)

Rashomon—A news­bet­ting site

ideasthete15 Oct 2024 18:15 UTC
23 points
8 comments1 min readLW link

On the Prac­ti­cal Ap­pli­ca­tions of Interpretability

Nick Jiang15 Oct 2024 17:18 UTC
1 point
0 comments7 min readLW link