9 Sep 2022 23:46 UTC

35 points

1 comment1 min readLW link

Web4/Heaven—The Simulation

Dunning K.9 Sep 2022 22:58 UTC

10 points

2 comments1 min readLW link

Evaluations project @ ARC is hiring a researcher and a webdev/engineer

Beth Barnes9 Sep 2022 22:46 UTC

99 points

7 comments10 min readLW link

Swap and Scale

Stephen Fowler9 Sep 2022 22:41 UTC

17 points

3 comments1 min readLW link

My emotional reaction to the current funding situation

Sam F. Brown9 Sep 2022 22:02 UTC

105 points

36 comments5 min readLW link

(sambrown.eu)

AlexaTM − 20 Billion Parameter Model With Impressive Performance

MrThink9 Sep 2022 21:46 UTC

5 points

0 comments1 min readLW link

[Fun][Link] Alignment SMBC Comic

Gunnar_Zarncke9 Sep 2022 21:38 UTC

7 points

2 comments1 min readLW link

(www.smbc-comics.com)

Gatekeeper Victory: AI Box Reflection

Double and DaemonicSigil

9 Sep 2022 21:38 UTC

6 points

6 comments9 min readLW link

Interpreting Affordable Housing

jefftk9 Sep 2022 19:40 UTC

16 points

0 comments1 min readLW link

(www.jefftk.com)

London Rationalish Meetup 2022-09-11

calmiguana9 Sep 2022 18:39 UTC

1 point

0 comments1 min readLW link

AI alignment with humans… but with which humans?

geoffreymiller9 Sep 2022 18:21 UTC

12 points

33 comments3 min readLW link

[Question] Should you refrain from having children because of the risk posed by artificial intelligence?

Mientras9 Sep 2022 17:39 UTC

17 points

31 comments1 min readLW link

Notes on Resolve

David Gross9 Sep 2022 16:42 UTC

9 points

1 comment31 min readLW link

ethics and anthropics of homomorphically encrypted computations

Tamsin Leake9 Sep 2022 10:49 UTC

47 points

49 comments3 min readLW link

(carado.moe)

Oversight Leagues: The Training Game as a Feature

Paul Bricman9 Sep 2022 10:08 UTC

20 points

6 comments10 min readLW link

Understanding and avoiding value drift

TurnTrout9 Sep 2022 4:16 UTC

43 points

9 comments6 min readLW link

Samotsvety’s AI risk forecasts

elifland9 Sep 2022 4:01 UTC

44 points

0 comments4 min readLW link

Most People Start With The Same Few Bad Ideas

johnswentworth9 Sep 2022 0:29 UTC

162 points

30 comments3 min readLW link

Monitoring for deceptive alignment

evhub8 Sep 2022 23:07 UTC

135 points

8 comments9 min readLW link

[An email with a bunch of links I sent an experienced ML researcher interested in learning about Alignment / x-safety.]

David Scott Krueger (formerly: capybaralet)8 Sep 2022 22:28 UTC

47 points

1 comment5 min readLW link

Progress links & tweets, 2022-09-08

jasoncrawford8 Sep 2022 20:43 UTC

13 points

3 comments1 min readLW link

(rootsofprogress.org)

Turning WhatsApp Chat Data into Prompt-Response Form for Fine-Tuning

hatta_afiq8 Sep 2022 20:05 UTC

1 point

0 comments1 min readLW link

Postmortem: Trying out for Manifold Markets

Milli | Martin and Austin Chen

8 Sep 2022 17:54 UTC

24 points

0 comments3 min readLW link

Thoughts on AGI consciousness / sentience

Steven Byrnes8 Sep 2022 16:40 UTC

38 points

37 comments6 min readLW link

A rough idea for solving ELK: An approach for training generalist agents like GATO to make plans and describe them to humans clearly and honestly.

Michael Soareverix8 Sep 2022 15:20 UTC

2 points

2 comments2 min readLW link

What Should AI Owe To Us? Accountable and Aligned AI Systems via Contractualist AI Alignment

xuan8 Sep 2022 15:04 UTC

32 points

15 comments25 min readLW link

ACX Book Review Discussion

Screwtape8 Sep 2022 14:22 UTC

5 points

0 comments1 min readLW link

Covid 9/8/22: Booster Boosting

Zvi8 Sep 2022 13:50 UTC

34 points

9 comments24 min readLW link

(thezvi.wordpress.com)

Solar Blackout Resistance

jefftk8 Sep 2022 13:30 UTC

69 points

32 comments3 min readLW link

(www.jefftk.com)

All AGI safety questions welcome (especially basic ones) [Sept 2022]

plex8 Sep 2022 11:56 UTC

22 points

48 comments2 min readLW link

[Question] Sequences/Eliezer essays beyond those in AI to Zombies?

Domenic8 Sep 2022 5:05 UTC

4 points

4 comments1 min readLW link

Linkpost: Github Copilot productivity experiment

Daniel Kokotajlo8 Sep 2022 4:41 UTC

88 points

4 comments1 min readLW link

(github.blog)

OpenPrinciples Bootcamp (Free) -- Reflect & Act on your Rationality Principles.

ti_guo8 Sep 2022 3:06 UTC

6 points

3 comments4 min readLW link

Searching for Modularity in Large Language Models

NickyP and Stephen Fowler

8 Sep 2022 2:25 UTC

44 points

3 comments14 min readLW link

90% of anything should be bad (& the precision-recall tradeoff)

cartografie8 Sep 2022 1:20 UTC

33 points

22 comments6 min readLW link

How to Do Research. v1

Pablo Repetto8 Sep 2022 1:08 UTC

29 points

4 comments41 min readLW link

(pabloernesto.github.io)

Galaxy Trucker Needs a New Second Half

jefftk7 Sep 2022 20:10 UTC

13 points

7 comments1 min readLW link

(www.jefftk.com)

[Question] In a lack of data, how should you weigh credences in theoretical physics’s Theories of Everything, or TOEs?

Noosphere897 Sep 2022 18:25 UTC

7 points

11 comments1 min readLW link

Generators Of Disagreement With AI Alignment

George3d67 Sep 2022 18:15 UTC

27 points

9 comments9 min readLW link

(www.epistem.ink)

Shrödinger’s lottery or: Why you are going to live forever

Chase Dowdell7 Sep 2022 18:13 UTC

1 point

2 comments4 min readLW link

Is training data going to be diluted by AI-generated content?

Hannes Thurnherr7 Sep 2022 18:13 UTC

10 points

7 comments1 min readLW link

It’s (not) how you use it

Eleni Angelou7 Sep 2022 17:15 UTC

8 points

1 comment2 min readLW link

First we shape our social graph; then it shapes us

Henrik Karlsson7 Sep 2022 15:50 UTC

52 points

6 comments8 min readLW link

(escapingflatland.substack.com)

AI-assisted list of ten concrete alignment things to do right now

lukehmiles7 Sep 2022 8:38 UTC

8 points

5 comments4 min readLW link

Can “Reward Economics” solve AI Alignment?

Q Home7 Sep 2022 7:58 UTC

3 points

15 comments18 min readLW link

Is there a list of projects to get started with Interpretability?

Franziska Fischer7 Sep 2022 4:27 UTC

8 points

2 comments1 min readLW link

Progress Report 7: making GPT go hurrdurr instead of brrrrrrr

Nathan Helm-Burger7 Sep 2022 3:28 UTC

21 points

0 comments4 min readLW link

Framing AI Childhoods

David Udell6 Sep 2022 23:40 UTC

37 points

8 comments4 min readLW link

Deleted comments archive

Said Achmiz6 Sep 2022 21:54 UTC

9 points

3 comments1 min readLW link

Guitar Pedals on Fiddle

jefftk6 Sep 2022 19:30 UTC

10 points

0 comments2 min readLW link

(www.jefftk.com)