Omicron Variant Post #2

Zvi29 Nov 2021 16:30 UTC

112 points

26 comments14 min readLW link

(thezvi.wordpress.com)

My take on higher-order game theory

Nisan30 Nov 2021 5:56 UTC

24 points

3 comments5 min readLW link

Christiano, Cotra, and Yudkowsky on AI progress

Eliezer Yudkowsky and Ajeya Cotra

25 Nov 2021 16:45 UTC

103 points

83 comments68 min readLW link

[Question] How do Bayesians tell what does and doesn’t count as evidence (which, e.g., hypotheses may render more or less probable if true)? Is it possible for something to fuzzily-be evidence?

LVSN30 Nov 2021 12:52 UTC

2 points

5 comments1 min readLW link

Watching Myself Program

matto29 Nov 2021 13:44 UTC

44 points

8 comments2 min readLW link

Memetic Hazards in Videogames

jimrandomh10 Sep 2010 2:22 UTC

123 points

163 comments3 min readLW link

The bonds of family and community: Poverty and cruelty among Russian peasants in the late 19th century

jasoncrawford28 Nov 2021 17:22 UTC

95 points

22 comments15 min readLW link

(rootsofprogress.org)

You are way more fallible than you think

shminux25 Nov 2021 5:52 UTC

4 points

13 comments2 min readLW link

Solve Corrigibility Week

elriggs28 Nov 2021 17:00 UTC

39 points

15 comments1 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

EfficientZero: human ALE sample-efficiency w/MuZero+self-supervised

gwern2 Nov 2021 2:32 UTC

134 points

52 comments1 min readLW link

(arxiv.org)

The Rationalists of the 1950s (and before) also called themselves “Rationalists”

Owain_Evans28 Nov 2021 20:17 UTC

145 points

11 comments3 min readLW link

How to Ignore Your Emotions (while also thinking you’re awesome at emotions)

Hazard31 Jul 2019 13:34 UTC

224 points

71 comments4 min readLW link 2 nominations 4 reviews

larger language models may disappoint you [or, an eternally unfinished draft]

nostalgebraist26 Nov 2021 23:08 UTC

162 points

13 comments31 min readLW link

Tears Must Flow

deluks91730 Nov 2021 18:37 UTC

4 points

5 comments1 min readLW link

[Question] How could a friendly AI deal with humans trying to sabotage it? (like how present day internet trolls introduce such problems)

M. Y. Zuo27 Nov 2021 22:07 UTC

7 points

10 comments1 min readLW link

Paxlovid Remains Illegal: 11/24 Update

Zvi24 Nov 2021 13:40 UTC

54 points

22 comments7 min readLW link

(thezvi.wordpress.com)

On the limits of idealized values

Joe Carlsmith22 Jun 2021 2:10 UTC

88 points

17 comments35 min readLW link

How To Get Into Independent Research On Alignment/Agency

johnswentworth19 Nov 2021 0:00 UTC

248 points

27 comments13 min readLW link