RSS

At­tain­able Utility Preser­va­tion: Em­piri­cal Results

22 Feb 2020 0:38 UTC
27 points
2 comments9 min readLW link

Will AI un­dergo dis­con­tin­u­ous progress?

SDM
21 Feb 2020 22:16 UTC
14 points
2 comments20 min readLW link

Cu­ri­os­ity Killed the Cat and the Asymp­tot­i­cally Op­ti­mal Agent

michaelcohen
20 Feb 2020 17:28 UTC
23 points
11 comments1 min readLW link

Tes­sel­lat­ing Hills: a toy model for demons in im­perfect search

DaemonicSigil
20 Feb 2020 0:12 UTC
57 points
11 comments2 min readLW link

On un­fix­ably un­safe AGI architectures

steve2152
19 Feb 2020 21:16 UTC
27 points
8 comments5 min readLW link

[AN #87]: What might hap­pen as deep learn­ing scales even fur­ther?

rohinmshah
19 Feb 2020 18:20 UTC
29 points
0 comments4 min readLW link
(mailchi.mp)

Stuck Exploration

Chris_Leong
19 Feb 2020 12:31 UTC
16 points
6 comments1 min readLW link

(In)ac­tion rollouts

Stuart_Armstrong
18 Feb 2020 14:48 UTC
11 points
2 comments2 min readLW link

Coun­ter­fac­tu­als ver­sus the laws of physics

Stuart_Armstrong
18 Feb 2020 13:21 UTC
16 points
0 comments1 min readLW link

Wire­head­ing and discontinuity

Michele Campolo
18 Feb 2020 10:49 UTC
15 points
0 comments3 min readLW link

Subagents and im­pact mea­sures: sum­mary tables

Stuart_Armstrong
17 Feb 2020 14:09 UTC
11 points
2 comments1 min readLW link

In­dex­i­cal im­pact measures

Stuart_Armstrong
17 Feb 2020 13:22 UTC
12 points
0 comments6 min readLW link

Step­wise in­ac­tion and non-in­dex­i­cal im­pact measures

Stuart_Armstrong
17 Feb 2020 10:32 UTC
12 points
7 comments1 min readLW link

At­tain­able Utility Preser­va­tion: Concepts

TurnTrout
17 Feb 2020 5:20 UTC
25 points
13 comments1 min readLW link

On the falsifi­a­bil­ity of hy­per­com­pu­ta­tion, part 2: finite in­put streams

jessicata
17 Feb 2020 3:51 UTC
21 points
4 comments4 min readLW link
(unstableontology.com)

Refer­ence Post: Triv­ial De­ci­sion Problem

Chris_Leong
15 Feb 2020 17:13 UTC
16 points
4 comments2 min readLW link

[Question] What is the differ­ence be­tween ro­bust­ness and in­ner al­ign­ment?

JanBrauner
15 Feb 2020 13:28 UTC
8 points
2 comments1 min readLW link

[Question] Does iter­ated am­plifi­ca­tion tackle the in­ner al­ign­ment prob­lem?

JanBrauner
15 Feb 2020 12:58 UTC
7 points
4 comments1 min readLW link

Bayesian Evolv­ing-to-Extinction

abramdemski
14 Feb 2020 23:55 UTC
35 points
8 comments5 min readLW link

The Catas­trophic Con­ver­gence Conjecture

TurnTrout
14 Feb 2020 21:16 UTC
31 points
12 comments7 min readLW link