All the posts I will never write

Self-Embedded Agent14 Aug 2022 18:29 UTC

41 points

7 comments8 min readLW link

AI Transparency: Why it’s critical and how to obtain it.

Zohar Jackson14 Aug 2022 10:31 UTC

6 points

1 comment5 min readLW link

A brief note on Simplicity Bias

Spencer Becker-Kahn14 Aug 2022 2:05 UTC

6 points

0 comments4 min readLW link

Against Relying on Evolution to Forecast AI Outcomes (Part 1)

Quintin Pope13 Aug 2022 22:15 UTC

35 points

4 comments8 min readLW link

Cultivating Valiance

Shos Tekofsky13 Aug 2022 18:47 UTC

29 points

4 comments4 min readLW link

An extended rocket alignment analogy

remember13 Aug 2022 18:22 UTC

25 points

3 comments4 min readLW link

[Question] What is an agent in reductionist materialism?

Valentine13 Aug 2022 15:39 UTC

18 points

15 comments1 min readLW link

Refine’s First Blog Post Day

adamShimi13 Aug 2022 10:23 UTC

46 points

3 comments1 min readLW link

The Dumbest Possible Gets There First

Artaxerxes13 Aug 2022 10:20 UTC

33 points

4 comments2 min readLW link

I missed the crux of the alignment problem the whole time

zeshen13 Aug 2022 10:11 UTC

47 points

5 comments3 min readLW link

goal-program bricks

carado13 Aug 2022 10:08 UTC

25 points

2 comments2 min readLW link

(carado.moe)

Shapes of Mind and Pluralism in Alignment

adamShimi13 Aug 2022 10:01 UTC

26 points

1 comment2 min readLW link

How I think about alignment

Linda Linsefors13 Aug 2022 10:01 UTC

22 points

8 comments5 min readLW link

Steelmining via Analogy

Paul Bricman13 Aug 2022 9:59 UTC

24 points

0 comments2 min readLW link

(paulbricman.com)

the Insulated Goal-Program idea

carado13 Aug 2022 9:57 UTC

24 points

2 comments2 min readLW link

(carado.moe)

Appendix: Jargon Dictionary

CFAR!Duncan13 Aug 2022 8:09 UTC

18 points

4 comments21 min readLW link

Appendix: Hamming Questions

CFAR!Duncan13 Aug 2022 8:07 UTC

25 points

0 comments2 min readLW link

Appendix: Building a Bugs List prompts

CFAR!Duncan13 Aug 2022 8:00 UTC

30 points

0 comments2 min readLW link

Gradient descent doesn’t select for inner search

Ivan Vendrov13 Aug 2022 4:15 UTC

24 points

9 comments4 min readLW link

[Question] How to bet against civilizational adequacy?

Wei_Dai12 Aug 2022 23:33 UTC

48 points

13 comments1 min readLW link