RSS

shminux

Karma: 28,669

Li­tany of a Bright Dilettante

shminux18 Apr 2013 5:06 UTC
89 points
71 comments1 min readLW link

Wire­head your Chickens

shminux20 Jun 2018 5:49 UTC
86 points
53 comments2 min readLW link

So you think you un­der­stand Quan­tum Mechanics

shminux22 Dec 2012 21:16 UTC
65 points
64 comments3 min readLW link

Top les­son from GPT: we will prob­a­bly de­stroy hu­man­ity “for the lulz” as soon as we are able.

shminux16 Apr 2023 20:27 UTC
65 points
28 comments1 min readLW link

Boe­ing 737 MAX MCAS as an agent cor­rigi­bil­ity failure

shminux16 Mar 2019 1:46 UTC
60 points
3 comments1 min readLW link

Re­spect Ch­ester­ton-Schel­ling Fences

shminux27 Feb 2023 0:09 UTC
58 points
17 comments1 min readLW link

Math­e­mat­ics as a lossy com­pres­sion al­gorithm gone wild

shminux6 Jun 2014 23:53 UTC
53 points
82 comments5 min readLW link

[LINK] Claus­trum Stim­u­la­tion Tem­porar­ily Turns Off Con­scious­ness in an oth­er­wise Awake Patient

shminux4 Jul 2014 20:00 UTC
51 points
43 comments1 min readLW link

How Might an Align­ment At­trac­tor Look like?

shminux28 Apr 2022 6:46 UTC
47 points
15 comments2 min readLW link

The Fermi Para­dox: What did Sand­berg, Drexler and Ord Really Dis­solve?

shminux8 Jul 2018 21:18 UTC
46 points
28 comments5 min readLW link

Scott Aaron­son on “Re­form AI Align­ment”

shminux20 Nov 2022 22:20 UTC
39 points
17 comments1 min readLW link
(scottaaronson.blog)

De­ci­sions are not about chang­ing the world, they are about learn­ing what world you live in

shminux28 Jul 2018 8:41 UTC
39 points
71 comments11 min readLW link

How can one ra­tio­nally have very high or very low prob­a­bil­ities of ex­tinc­tion in a pre-paradig­matic field?

shminux30 Apr 2023 21:53 UTC
39 points
15 comments1 min readLW link

Write posts busi­ness-like, not story-like

shminux5 May 2022 20:13 UTC
39 points
10 comments1 min readLW link

[Question] Is there any dis­cus­sion on avoid­ing be­ing Dutch-booked or oth­er­wise taken ad­van­tage of one’s bounded ra­tio­nal­ity by re­fus­ing to en­gage?

shminux7 Nov 2022 2:36 UTC
38 points
29 comments1 min readLW link

[Question] Since figur­ing out hu­man val­ues is hard, what about, say, mon­key val­ues?

shminux1 Jan 2020 21:56 UTC
37 points
13 comments1 min readLW link

[LINK] Larry = Harry sans magic? Google vs. Death

shminux18 Sep 2013 16:49 UTC
36 points
55 comments1 min readLW link

The Per­va­sive Illu­sion of See­ing the Com­plete World

shminux9 Feb 2023 6:47 UTC
34 points
1 comment2 min readLW link

[Link] The Stan­ford Su­per­man Ex­per­i­ment: An­chor­ing Em­pa­thy?

shminux1 Feb 2013 17:31 UTC
32 points
11 comments1 min readLW link

[Question] Why are we sure that AI will “want” some­thing?

shminux16 Sep 2022 20:35 UTC
31 points
57 comments1 min readLW link