26 Sep 2022 23:40 UTC

59 points

1 comment5 min readLW link

(acesounderglass.com)

D&D.Sci September 2022 Evaluation and Ruleset

abstractapplic26 Sep 2022 22:19 UTC

26 points

5 comments3 min readLW link

[MLSN #5]: Prize Compilation

Dan H26 Sep 2022 21:55 UTC

14 points

1 comment2 min readLW link

Loss of Alignment is not the High-Order Bit for AI Risk

yieldthought26 Sep 2022 21:16 UTC

14 points

18 comments2 min readLW link

Triangle Opportunity

Alex Beyman26 Sep 2022 20:42 UTC

52 points

10 comments54 min readLW link

Inverse Scaling Prize: Round 1 Winners

Ethan Perez and Ian McKenzie

26 Sep 2022 19:57 UTC

93 points

16 comments4 min readLW link

(irmckenzie.co.uk)

[Question] Does the existence of shared human values imply alignment is “easy”?

Morpheus26 Sep 2022 18:01 UTC

7 points

15 comments1 min readLW link

Meetup: Madison, WI (Oct 8)

svfritz26 Sep 2022 17:55 UTC

1 point

0 comments1 min readLW link

Ambiguity in Prediction Market Resolution is Harmful

aphyer26 Sep 2022 16:22 UTC

69 points

17 comments5 min readLW link

Framery Phone Booth CO2 Accumulation

jefftk26 Sep 2022 16:10 UTC

25 points

0 comments1 min readLW link

(www.jefftk.com)

[Question] How can I remove the launch button from my LW home page?

sudo26 Sep 2022 15:15 UTC

8 points

4 comments1 min readLW link

Brief Notes on Transformers

Adam Jermyn26 Sep 2022 14:46 UTC

46 points

3 comments2 min readLW link

You are Underestimating The Likelihood That Convergent Instrumental Subgoals Lead to Aligned AGI

Mark Neyer26 Sep 2022 14:22 UTC

3 points

6 comments3 min readLW link

Climate-contingent Finance, and A Generalized Mechanism for X-Risk Reduction Financing

John Nay26 Sep 2022 13:23 UTC

0 points

2 comments1 min readLW link

Self-Control Secrets of the Puritan Masters

David Hugh-Jones26 Sep 2022 9:04 UTC

62 points

3 comments5 min readLW link

(wyclif.substack.com)

How I buy things when Lightcone wants them fast

jacobjacob26 Sep 2022 5:02 UTC

218 points

21 comments8 min readLW link

Oren’s Field Guide of Bad AGI Outcomes

Oren Montano26 Sep 2022 4:06 UTC

0 points

0 comments1 min readLW link

On Generality

Oren Montano26 Sep 2022 4:06 UTC

2 points

0 comments5 min readLW link

Planning capacity and daemons

lukehmiles26 Sep 2022 0:15 UTC

2 points

0 comments5 min readLW link

Planning a Loft Bed

jefftk26 Sep 2022 0:10 UTC

15 points

15 comments2 min readLW link

(www.jefftk.com)

Becoming Black Boxish

vitaliya25 Sep 2022 23:35 UTC

16 points

0 comments2 min readLW link

Announcing Balsa Research

Zvi25 Sep 2022 22:50 UTC

235 points

64 comments2 min readLW link 1 review

(thezvi.wordpress.com)

[Question] How to learn: Struggle VS Lookup-Table?

NicholasKross25 Sep 2022 21:58 UTC

15 points

2 comments2 min readLW link

An Unexpected GPT-3 Decision in a Simple Gamble

hatta_afiq25 Sep 2022 16:46 UTC

8 points

4 comments1 min readLW link

“Agency” needs nuance

Evie Cottrell25 Sep 2022 7:40 UTC

23 points

1 comment14 min readLW link

Acceptance and Commitment Therapy (ACT) 101

Evie Cottrell25 Sep 2022 7:25 UTC

5 points

2 comments8 min readLW link

Bathroom Construction Cost Comparison

jefftk25 Sep 2022 2:30 UTC

11 points

0 comments2 min readLW link

(www.jefftk.com)

Prioritizing the Arts in response to AI automation

Casey25 Sep 2022 2:25 UTC

18 points

11 comments2 min readLW link

UI/UX From the Dark Ages

shminux25 Sep 2022 1:53 UTC

25 points

15 comments2 min readLW link

P(misalignment x-risk|AGI) is small #[Future Fund worldview prize]

Dibbu Dibbu24 Sep 2022 23:54 UTC

−18 points

0 comments4 min readLW link

Everybody Comes Back

Alex Beyman24 Sep 2022 23:53 UTC

8 points

0 comments27 min readLW link

[Question] Papers to start getting into NLP-focused alignment research

Feraidoon24 Sep 2022 23:53 UTC

6 points

0 comments1 min readLW link

Whose Fault?

Markovia24 Sep 2022 23:53 UTC

1 point

0 comments1 min readLW link

Brain-over-body biases, and the embodied value problem in AI alignment

geoffreymiller24 Sep 2022 22:24 UTC

10 points

6 comments25 min readLW link

Opt out from the Funni

Coafos24 Sep 2022 22:07 UTC

8 points

1 comment2 min readLW link

AI coöperation is more possible than you think

42317524 Sep 2022 21:26 UTC

7 points

0 comments2 min readLW link

“Cotton Gin” AI Risk

42317524 Sep 2022 21:26 UTC

7 points

3 comments2 min readLW link

Two reasons we might be closer to solving alignment than it seems

KatWoods and AmberDawn

24 Sep 2022 20:00 UTC

57 points

9 comments4 min readLW link

Orexin and the quest for more waking hours

ChristianKl24 Sep 2022 19:54 UTC

129 points

39 comments5 min readLW link

AI Safety Discord community (requesting help!)

Casey24 Sep 2022 17:35 UTC

8 points

0 comments2 min readLW link

[Question] I’m planning to start creating more write-ups summarizing my thoughts on various issues, mostly related to AI existential safety. What do you want to hear my nuanced takes on?

David Scott Krueger (formerly: capybaralet)24 Sep 2022 12:38 UTC

9 points

10 comments1 min readLW link

Attempts at Forwarding Speed Priors

james.lucassen and evhub

24 Sep 2022 5:49 UTC

30 points

2 comments18 min readLW link

Announcing $5,000 bounty for (responsibly) ending malaria

lc24 Sep 2022 4:28 UTC

116 points

40 comments4 min readLW link

[Question] Why Do AI researchers Rate the Probability of Doom So Low?

Aorou24 Sep 2022 2:33 UTC

7 points

6 comments3 min readLW link

Set List Approaches

jefftk24 Sep 2022 2:30 UTC

9 points

0 comments12 min readLW link

(www.jefftk.com)

A ranked link of LessWrong tags/concepts

peterslattery24 Sep 2022 0:11 UTC

16 points

4 comments1 min readLW link

[Question] Posts with clickable sections of images?

NoBadCake23 Sep 2022 23:19 UTC

1 point

5 comments1 min readLW link

Under what circumstances have governments cancelled AI-type systems?

David Gross23 Sep 2022 21:11 UTC

7 points

1 comment1 min readLW link

(www.carnegieuktrust.org.uk)

There are no rules

unoptimal23 Sep 2022 20:47 UTC

34 points

2 comments5 min readLW link

Interpreting Neural Networks through the Polytope Lens

Sid Black, Lee Sharkey, Connor Leahy, beren, CRG, merizian, Eric Winsor and Dan Braun

23 Sep 2022 17:58 UTC

136 points

29 comments33 min readLW link