RSS

Stuart_Armstrong(Stuart Armstrong)

Karma: 22,237

The AI in a box boxes you

Stuart_Armstrong
2 Feb 2010 10:10 UTC
121 points
390 comments1 min readLW link

The differ­ent types (not sizes!) of infinity

Stuart_Armstrong
28 Jan 2018 11:14 UTC
104 points
31 comments1 min readLW link

Just an­other day in utopia

Stuart_Armstrong
25 Dec 2011 9:37 UTC
88 points
116 comments13 min readLW link

And the AI would have got away with it too, if...

Stuart_Armstrong
22 May 2019 21:35 UTC
76 points
4 comments1 min readLW link

“But that’s your job”: why or­gani­sa­tions can work

Stuart_Armstrong
5 Feb 2020 12:25 UTC
73 points
11 comments4 min readLW link

Why we need a *the­ory* of hu­man values

Stuart_Armstrong
5 Dec 2018 16:00 UTC
68 points
15 comments4 min readLW link

Con­test: $1,000 for good ques­tions to ask to an Or­a­cle AI

Stuart_Armstrong
31 Jul 2019 18:48 UTC
68 points
154 comments3 min readLW link

Prob­lems with Am­plifi­ca­tion/​Distillation

Stuart_Armstrong
27 Mar 2018 11:12 UTC
67 points
7 comments10 min readLW link

Have you felt ex­iert yet?

Stuart_Armstrong
5 Jan 2018 17:03 UTC
66 points
7 comments1 min readLW link

mAIry’s room: AI rea­son­ing to solve philo­soph­i­cal problems

Stuart_Armstrong
5 Mar 2019 20:24 UTC
64 points
27 comments6 min readLW link

What would con­vince you you’d won the lot­tery?

Stuart_Armstrong
10 Oct 2017 13:45 UTC
63 points
11 comments4 min readLW link

Re­search Agenda v0.9: Syn­the­sis­ing a hu­man’s prefer­ences into a util­ity function

Stuart_Armstrong
17 Jun 2019 17:46 UTC
63 points
20 comments33 min readLW link

Re­solv­ing hu­man val­ues, com­pletely and adequately

Stuart_Armstrong
30 Mar 2018 3:35 UTC
55 points
28 comments12 min readLW link

AI timeline pre­dic­tions: are we get­ting bet­ter?

Stuart_Armstrong
17 Aug 2012 7:07 UTC
54 points
81 comments4 min readLW link

Hu­mans can be as­signed any val­ues what­so­ever…

Stuart_Armstrong
5 Nov 2018 14:26 UTC
54 points
24 comments4 min readLW link

The Oc­to­pus, the Dolphin and Us: a Great Filter tale

Stuart_Armstrong
3 Sep 2014 21:37 UTC
53 points
234 comments3 min readLW link

Let’s split the cake, length­wise, up­wise and slantwise

Stuart_Armstrong
25 Oct 2010 13:15 UTC
51 points
29 comments4 min readLW link

An­thropic sig­na­ture: strange anti-correlations

Stuart_Armstrong
21 Oct 2014 16:59 UTC
51 points
25 comments1 min readLW link

At­tain­able util­ity has a sub­agent problem

Stuart_Armstrong
28 Jan 2020 15:28 UTC
51 points
17 comments4 min readLW link

Assess­ing Kurzweil: the results

Stuart_Armstrong
16 Jan 2013 16:51 UTC
50 points
61 comments2 min readLW link