Risk and uncertainty: A false dichotomy?

18 Jan 2020 3:09 UTC

3 points

0 comments20 min readLW link

Being a Robust, Coherent Agent (V2)

18 Jan 2020 2:06 UTC

93 points

21 comments7 min readLW link 2 nominations 2 reviews

“How quickly can you get this done?” (estimating workload)

18 Jan 2020 0:10 UTC

8 points

8 comments4 min readLW link

Studying Early Stage Science: Research Program Introduction

17 Jan 2020 22:12 UTC

12 points

0 comments15 min readLW link

(medium.com)

Conversational Cultures: Combat vs Nurture (V2)

17 Jan 2020 20:23 UTC

129 points

85 comments9 min readLW link 2 nominations 3 reviews

[Question] How does a Living Being solve the problem of Subsystem Alignment?

17 Jan 2020 9:32 UTC

3 points

2 comments1 min readLW link

Can we always assign, and make sense of, subjective probabilities?

17 Jan 2020 3:05 UTC

10 points

12 comments13 min readLW link

Against Rationalization II: Sequence Recap

16 Jan 2020 22:51 UTC

6 points

2 comments1 min readLW link

Using Expert Disagreement

16 Jan 2020 22:42 UTC

12 points

1 comment5 min readLW link

Reality-Revealing and Reality-Masking Puzzles

16 Jan 2020 16:15 UTC

198 points

37 comments13 min readLW link

How to Escape From Immoral Mazes

16 Jan 2020 13:10 UTC

53 points

10 comments19 min readLW link

(thezvi.wordpress.com)

Testing for Rationalization

16 Jan 2020 8:12 UTC

18 points

0 comments2 min readLW link

[Question] How useful do you think participating to the Human Microbiome Project would be?

15 Jan 2020 23:51 UTC

3 points

0 comments1 min readLW link

The Alignment-Competence Trade-Off, Part 1: Coalition Size and Signaling Costs

15 Jan 2020 23:10 UTC

29 points

2 comments3 min readLW link

(theconsequentialist.wordpress.com)

In Defense of the Arms Races… that End Arms Races

15 Jan 2020 21:30 UTC

29 points

5 comments3 min readLW link

(theconsequentialist.wordpress.com)

Fire Alarm for AGI

15 Jan 2020 20:41 UTC

1 point

0 comments1 min readLW link

(blog.acolyer.org)

Go F*** Someone

15 Jan 2020 18:39 UTC

11 points

12 comments8 min readLW link

[AN #82]: How OpenAI Five distributed their training computation

15 Jan 2020 18:20 UTC

19 points

0 comments8 min readLW link

(mailchi.mp)

ACDT: a hack-y acausal decision theory

Stuart_Armstrong

15 Jan 2020 17:22 UTC

44 points

8 comments7 min readLW link

In defense of deviousness

Juan Andrés Hurtado Baeza

15 Jan 2020 11:56 UTC

14 points

5 comments4 min readLW link

(medium.com)