RSS

Stuart_Armstrong(Stuart Armstrong)

Karma: 23,292

Hu­mans are stun­ningly ra­tio­nal and stun­ningly irrational

Stuart_Armstrong23 Oct 2020 14:13 UTC
21 points
4 comments2 min readLW link

Knowl­edge, ma­nipu­la­tion, and free will

Stuart_Armstrong13 Oct 2020 17:47 UTC
31 points
15 comments3 min readLW link

De­hu­man­i­sa­tion *er­rors*

Stuart_Armstrong23 Sep 2020 9:51 UTC
13 points
0 comments1 min readLW link

An­thro­po­mor­phi­sa­tion vs value learn­ing: type 1 vs type 2 errors

Stuart_Armstrong22 Sep 2020 10:46 UTC
16 points
10 comments1 min readLW link

Tech­ni­cal model re­fine­ment formalism

Stuart_Armstrong27 Aug 2020 11:54 UTC
9 points
0 comments6 min readLW link

Model splin­ter­ing: mov­ing from one im­perfect model to another

Stuart_Armstrong27 Aug 2020 11:53 UTC
34 points
3 comments33 min readLW link

Learn­ing hu­man prefer­ences: black-box, white-box, and struc­tured white-box access

Stuart_Armstrong24 Aug 2020 11:42 UTC
23 points
9 comments6 min readLW link

AI safety as feather­less bipeds *with broad flat nails*

Stuart_Armstrong19 Aug 2020 10:22 UTC
35 points
1 comment1 min readLW link

Learn­ing hu­man prefer­ences: op­ti­mistic and pes­simistic scenarios

Stuart_Armstrong18 Aug 2020 13:05 UTC
26 points
6 comments6 min readLW link

Strong im­pli­ca­tion of prefer­ence uncertainty

Stuart_Armstrong12 Aug 2020 19:02 UTC
20 points
3 comments2 min readLW link

“Go west, young man!”—Prefer­ences in (im­perfect) maps

Stuart_Armstrong31 Jul 2020 7:50 UTC
21 points
10 comments3 min readLW link

Learn­ing Values in Practice

Stuart_Armstrong20 Jul 2020 18:38 UTC
24 points
0 comments5 min readLW link

The Gold­bach con­jec­ture is prob­a­bly cor­rect; so was Fer­mat’s last theorem

Stuart_Armstrong14 Jul 2020 19:30 UTC
75 points
14 comments4 min readLW link

Why is the im­pact penalty time-in­con­sis­tent?

Stuart_Armstrong9 Jul 2020 17:26 UTC
16 points
1 comment2 min readLW link

Dy­namic in­con­sis­tency of the in­ac­tion and ini­tial state baseline

Stuart_Armstrong7 Jul 2020 12:02 UTC
30 points
8 comments2 min readLW link

Models, myths, dreams, and Cheshire cat grins

Stuart_Armstrong24 Jun 2020 10:50 UTC
21 points
7 comments2 min readLW link

Re­sults of $1,000 Or­a­cle con­test!

Stuart_Armstrong17 Jun 2020 17:44 UTC
55 points
2 comments1 min readLW link

Com­par­ing re­ward learn­ing/​re­ward tam­per­ing formalisms

Stuart_Armstrong21 May 2020 12:03 UTC
9 points
3 comments3 min readLW link

Prob­a­bil­ities, weights, sums: pretty much the same for re­ward functions

Stuart_Armstrong20 May 2020 15:19 UTC
11 points
1 comment2 min readLW link

Learn­ing and ma­nipu­lat­ing learning

Stuart_Armstrong19 May 2020 13:02 UTC
40 points
4 comments10 min readLW link