Infra-Bayesian physicalism: proofs part II

Vanessa Kosoy30 Nov 2021 22:27 UTC

7 points

0 comments23 min readLW link

Infra-Bayesian physicalism: proofs part I

Vanessa Kosoy30 Nov 2021 22:26 UTC

7 points

0 comments22 min readLW link

Infra-Bayesian physicalism: a formal theory of naturalized induction

Vanessa Kosoy30 Nov 2021 22:25 UTC

37 points

0 comments39 min readLW link

My take on higher-order game theory

Nisan30 Nov 2021 5:56 UTC

24 points

2 comments5 min readLW link

Visible Thoughts Project and Bounty Announcement

So8res30 Nov 2021 0:19 UTC

199 points

61 comments12 min readLW link

Soares, Tallinn, and Yudkowsky discuss AGI cognition

So8res, Eliezer Yudkowsky and jaan

29 Nov 2021 19:26 UTC

99 points

22 comments40 min readLW link

Comments on Allan Dafoe on AI Governance

alexflint29 Nov 2021 16:16 UTC

16 points

0 comments7 min readLW link

Solve Corrigibility Week

elriggs28 Nov 2021 17:00 UTC

39 points

15 comments1 min readLW link

Christiano, Cotra, and Yudkowsky on AI progress

Eliezer Yudkowsky and Ajeya Cotra

25 Nov 2021 16:45 UTC

103 points

82 comments68 min readLW link

[AN #169]: Collaborating with humans without human data

rohinmshah24 Nov 2021 18:30 UTC

33 points

0 comments8 min readLW link

(mailchi.mp)

AI Tracker: monitoring current and near-future risks from superscale models

Edouard Harris and Jeremie Harris

23 Nov 2021 19:16 UTC

59 points

7 comments3 min readLW link

(aitracker.org)

AI Safety Needs Great Engineers

Andy Jones23 Nov 2021 15:40 UTC

75 points

33 comments4 min readLW link

Integrating Three Models of (Human) Cognition

jbkjr23 Nov 2021 1:06 UTC

26 points

1 comment32 min readLW link

Potential Alignment mental tool: Keeping track of the types

Donald Hobson22 Nov 2021 20:05 UTC

28 points

1 comment2 min readLW link

Yudkowsky and Christiano discuss “Takeoff Speeds”

Eliezer Yudkowsky22 Nov 2021 19:35 UTC

171 points

157 comments60 min readLW link

Morally underdefined situations can be deadly

Stuart_Armstrong22 Nov 2021 14:48 UTC

17 points

8 comments2 min readLW link

From language to ethics by automated reasoning

Michele Campolo21 Nov 2021 15:16 UTC

4 points

5 comments6 min readLW link

Corrigibility Can Be VNM-Incoherent

TurnTrout20 Nov 2021 0:30 UTC

61 points

23 comments7 min readLW link

More detailed proposal for measuring alignment of current models

Beth Barnes20 Nov 2021 0:03 UTC

27 points

0 comments8 min readLW link

Goodhart: Endgame

Charlie Steiner19 Nov 2021 1:26 UTC

22 points

3 comments7 min readLW link