RSS

Matthew Barnett

Karma: 1,173
Page 1

In­ner al­ign­ment re­quires mak­ing as­sump­tions about hu­man values

Matthew Barnett
20 Jan 2020 18:38 UTC
23 points
7 comments4 min readLW link

Mal­ign gen­er­al­iza­tion with­out in­ter­nal search

Matthew Barnett
12 Jan 2020 18:03 UTC
26 points
11 comments4 min readLW link

Might hu­mans not be the most in­tel­li­gent an­i­mals?

Matthew Barnett
23 Dec 2019 21:50 UTC
55 points
40 comments3 min readLW link

Is the term mesa op­ti­mizer too nar­row?

Matthew Barnett
14 Dec 2019 23:20 UTC
25 points
21 comments1 min readLW link

Ex­plain­ing why false ideas spread is more fun than why true ones do

Matthew Barnett
24 Nov 2019 20:21 UTC
30 points
6 comments1 min readLW link

Will trans­parency help catch de­cep­tion? Per­haps not

Matthew Barnett
4 Nov 2019 20:52 UTC
46 points
5 comments7 min readLW link

Two ex­pla­na­tions for vari­a­tion in hu­man abilities

Matthew Barnett
25 Oct 2019 22:06 UTC
74 points
18 comments6 min readLW link

Mis­con­cep­tions about con­tin­u­ous takeoff

Matthew Barnett
8 Oct 2019 21:31 UTC
71 points
36 comments4 min readLW link

A sim­ple en­vi­ron­ment for show­ing mesa misalignment

Matthew Barnett
26 Sep 2019 4:44 UTC
64 points
9 comments2 min readLW link

One Way to Think About ML Transparency

Matthew Barnett
2 Sep 2019 23:27 UTC
20 points
25 comments5 min readLW link

[Question] Has Moore’s Law ac­tu­ally slowed down?

Matthew Barnett
20 Aug 2019 19:18 UTC
13 points
8 comments1 min readLW link

[Question] How can you use mu­sic to boost learn­ing?

Matthew Barnett
17 Aug 2019 6:59 UTC
10 points
1 comment1 min readLW link

A Primer on Ma­trix Calcu­lus, Part 3: The Chain Rule

Matthew Barnett
17 Aug 2019 1:50 UTC
10 points
4 comments6 min readLW link

A Primer on Ma­trix Calcu­lus, Part 2: Ja­co­bi­ans and other fun

Matthew Barnett
15 Aug 2019 1:13 UTC
22 points
6 comments6 min readLW link

A Primer on Ma­trix Calcu­lus, Part 1: Ba­sic review

Matthew Barnett
12 Aug 2019 23:44 UTC
23 points
2 comments7 min readLW link

Matthew Bar­nett’s Shortform

Matthew Barnett
9 Aug 2019 5:17 UTC
7 points
146 comments1 min readLW link

Why Gra­di­ents Van­ish and Explode

Matthew Barnett
9 Aug 2019 2:54 UTC
27 points
9 comments3 min readLW link

Four Ways An Im­pact Mea­sure Could Help Alignment

Matthew Barnett
8 Aug 2019 0:10 UTC
21 points
1 comment8 min readLW link

Un­der­stand­ing Re­cent Im­pact Measures

Matthew Barnett
7 Aug 2019 4:57 UTC
17 points
6 comments7 min readLW link

[Question] What are the best re­sources for ex­am­in­ing the ev­i­dence for an­thro­pogenic cli­mate change?

Matthew Barnett
6 Aug 2019 2:53 UTC
11 points
8 comments1 min readLW link