RSS

Inac­cessible information

paulfchristiano
3 Jun 2020 5:10 UTC
55 points
7 comments14 min readLW link
(ai-alignment.com)

[AN #102]: Meta learn­ing by GPT-3, and a list of full pro­pos­als for AI alignment

rohinmshah
3 Jun 2020 17:20 UTC
25 points
2 comments10 min readLW link
(mailchi.mp)

Con­cep­tual en­g­ineer­ing: the rev­olu­tion in philos­o­phy you’ve never heard of

Suspended Reason
2 Jun 2020 18:30 UTC
56 points
12 comments21 min readLW link

Covid-19: My Cur­rent Model

Zvi
31 May 2020 17:40 UTC
128 points
29 comments19 min readLW link
(thezvi.wordpress.com)

Pos­si­ble take­aways from the coro­n­avirus pan­demic for slow AI takeoff

Vika
31 May 2020 17:51 UTC
96 points
10 comments3 min readLW link

An overview of 11 pro­pos­als for build­ing safe ad­vanced AI

evhub
29 May 2020 20:38 UTC
135 points
16 comments38 min readLW link

May Gw­ern.net newslet­ter (w/​GPT-3 com­men­tary)

gwern
2 Jun 2020 15:40 UTC
29 points
1 comment1 min readLW link
(www.gwern.net)

Build­ing brain-in­spired AGI is in­finitely eas­ier than un­der­stand­ing the brain

steve2152
2 Jun 2020 14:13 UTC
28 points
6 comments7 min readLW link

GPT-3: A Summary

leogao
2 Jun 2020 18:14 UTC
17 points
0 comments1 min readLW link
(leogao.dev)

Feed­back is cen­tral to agency

alexflint
1 Jun 2020 12:56 UTC
27 points
0 comments3 min readLW link

How to (not) do a liter­a­ture review

Katarina Slama
30 May 2020 0:11 UTC
62 points
4 comments6 min readLW link
(katarinaslama.github.io)

Spar­sity and in­ter­pretabil­ity?

1 Jun 2020 13:25 UTC
24 points
1 comment7 min readLW link

The Pre­sump­tu­ous Philoso­pher, self-lo­cat­ing in­for­ma­tion, and Solomonoff induction

Charlie Steiner
31 May 2020 16:35 UTC
34 points
26 comments3 min readLW link

[Question] Un­der which con­di­tions are hu­man be­ings most likely to be al­tru­is­ti­cally mo­ti­vated?

toonalfrink
1 Jun 2020 19:16 UTC
16 points
5 comments1 min readLW link

OpenAI an­nounces GPT-3

gwern
29 May 2020 1:49 UTC
56 points
23 comments1 min readLW link
(arxiv.org)

In­tro­duc­tion to Ex­is­ten­tial Risks from Ar­tifi­cial In­tel­li­gence, for an EA audience

JoshuaFox
2 Jun 2020 8:30 UTC
9 points
1 comment1 min readLW link

Bak­ing is Not a Ritual

Sisi Cheng
25 May 2020 18:08 UTC
90 points
25 comments4 min readLW link

On the con­struc­tion of the self

Kaj_Sotala
29 May 2020 13:04 UTC
43 points
16 comments17 min readLW link

Why We Age, Part 2: Non-adap­tive theories

willbradshaw
26 May 2020 17:41 UTC
71 points
21 comments11 min readLW link
(apomorphic.com)

Over­cor­rect­ing As De­liber­ate Practice

lifelonglearner
1 Jun 2020 6:26 UTC
16 points
0 comments1 min readLW link