RSS

Noosphere89

Karma: 3,435

The real rea­son AI bench­marks haven’t re­flected eco­nomic impacts

Noosphere89Apr 15, 2025, 1:44 PM
14 points
0 comments1 min readLW link
(epoch.ai)

[Question] Does the AI con­trol agenda broadly rely on no FOOM be­ing pos­si­ble?

Noosphere89Mar 29, 2025, 7:38 PM
22 points
3 comments1 min readLW link

Can a finite phys­i­cal de­vice be Tur­ing equiv­a­lent?

Noosphere89Mar 6, 2025, 3:02 PM
0 points
10 comments2 min readLW link
(lifeiscomputation.com)

[Question] When is re­ward ever the op­ti­miza­tion tar­get?

Noosphere89Oct 15, 2024, 3:09 PM
37 points
17 comments1 min readLW link

[Question] What does it mean for an event or ob­ser­va­tion to have prob­a­bil­ity 0 or 1 in Bayesian terms?

Noosphere89Sep 17, 2024, 5:28 PM
1 point
22 comments1 min readLW link

My dis­agree­ments with “AGI ruin: A List of Lethal­ities”

Noosphere89Sep 15, 2024, 5:22 PM
36 points
46 comments18 min readLW link

[Question] Does a time-re­versible phys­i­cal law/​Cel­lu­lar Au­toma­ton always im­ply the First Law of Ther­mo­dy­nam­ics?

Noosphere89Aug 30, 2024, 3:12 PM
7 points
11 comments1 min readLW link

Fran­cois Chol­let in­ad­ver­tently limits his claim on ARC-AGI

Noosphere89Jul 16, 2024, 5:32 PM
12 points
3 comments1 min readLW link
(x.com)

The prob­lems with the con­cept of an in­fo­haz­ard as used by the LW com­mu­nity [Linkpost]

Noosphere89Dec 22, 2023, 4:13 PM
75 points
43 comments3 min readLW link
(www.beren.io)

[Question] What’s the min­i­mal ad­di­tive con­stant for Kol­mogorov Com­plex­ity that a pro­gram­ming lan­guage can achieve?

Noosphere89Dec 20, 2023, 3:36 PM
11 points
15 comments1 min readLW link

Ar­gu­ments for op­ti­mism on AI Align­ment (I don’t en­dorse this ver­sion, will re­u­pload a new ver­sion soon.)

Noosphere89Oct 15, 2023, 2:51 PM
28 points
129 comments25 min readLW link

Hilbert’s Triumph, Church and Tur­ing’s failure, and what it means (Post #2)

Noosphere89Jul 30, 2023, 2:33 PM
−5 points
16 comments15 min readLW link

[Question] Does de­cid­abil­ity of a the­ory im­ply com­plete­ness of the the­ory?

Noosphere89Jul 29, 2023, 11:53 PM
6 points
12 comments1 min readLW link

Why you can’t treat de­cid­abil­ity and com­plex­ity as a con­stant (Post #1)

Noosphere89Jul 26, 2023, 5:54 PM
6 points
13 comments5 min readLW link

An Opinionated Guide to Com­putabil­ity and Com­plex­ity (Post #0)

Noosphere89Jul 24, 2023, 5:53 PM
10 points
10 comments3 min readLW link

[Question] Con­di­tional on liv­ing in a AI safety/​al­ign­ment by de­fault uni­verse, what are the im­pli­ca­tions of this as­sump­tion be­ing true?

Noosphere89Jul 17, 2023, 2:44 PM
26 points
10 comments1 min readLW link

A po­ten­tially high im­pact differ­en­tial tech­nolog­i­cal de­vel­op­ment area

Noosphere89Jun 8, 2023, 2:33 PM
5 points
2 comments2 min readLW link

[Question] Are com­pu­ta­tion­ally com­plex al­gorithms ex­pen­sive to have, ex­pen­sive to op­er­ate, or both?

Noosphere89Jun 2, 2023, 5:50 PM
7 points
5 comments1 min readLW link

[Question] Does re­versible com­pu­ta­tion let you com­pute the com­plex­ity class PSPACE as effi­ciently as nor­mal com­put­ers com­pute the com­plex­ity class P?

Noosphere89May 9, 2023, 1:18 PM
6 points
14 comments1 min readLW link

[Question] Are there AI poli­cies that are ro­bustly net-pos­i­tive even when con­sid­er­ing differ­ent AI sce­nar­ios?

Noosphere89Apr 23, 2023, 9:46 PM
11 points
1 comment1 min readLW link