12 Aug 2024 22:23 UTC

42 points

14 comments21 min readLW link

SYSTEMA ROBOTICA

Ali Ahmed12 Aug 2024 20:34 UTC

12 points

2 comments30 min readLW link

Extracting SAE task features for in-context learning

Dmitrii Kharlapenko, neverix, Neel Nanda and Arthur Conmy

12 Aug 2024 20:34 UTC

31 points

1 comment9 min readLW link

Hyppotherapy

Marius Adrian Nicoară12 Aug 2024 20:07 UTC

−3 points

0 comments1 min readLW link

Californians, tell your reps to vote yes on SB 1047!

Holly_Elmore12 Aug 2024 19:50 UTC

40 points

24 comments1 min readLW link

[LDSL#5] Comparison and magnitude/diminishment

tailcalled12 Aug 2024 18:47 UTC

21 points

0 comments2 min readLW link

In Defense of Open-Minded UDT

abramdemski12 Aug 2024 18:27 UTC

72 points

27 comments11 min readLW link

Humanity isn’t remotely longtermist, so arguments for AGI x-risk should focus on the near term

Seth Herd12 Aug 2024 18:10 UTC

46 points

10 comments1 min readLW link

Creating a “Conscience Calculator” to Guard-Rail an AGI

sweenesm12 Aug 2024 16:03 UTC

−2 points

0 comments13 min readLW link

Shifting Headspaces—Transitional Beast-Mode

Jonathan Moregård12 Aug 2024 13:02 UTC

36 points

9 comments2 min readLW link

(honestliving.substack.com)

Simultaneous Footbass and Footdrums II

jefftk11 Aug 2024 23:50 UTC

9 points

0 comments1 min readLW link

(www.jefftk.com)

CultFrisbee

Gauraventh11 Aug 2024 21:36 UTC

16 points

3 comments1 min readLW link

(y1d2.com)

Pleasure and suffering are not conceptual opposites

MichaelStJules11 Aug 2024 18:32 UTC

10 points

0 comments1 min readLW link

Computational irreducibility challenges the simulation hypothesis

Clément L11 Aug 2024 16:14 UTC

3 points

15 comments7 min readLW link

[LDSL#4] Root cause analysis versus effect size estimation

tailcalled11 Aug 2024 16:12 UTC

29 points

0 comments2 min readLW link

Closed to Interpretation

Yeshua God11 Aug 2024 15:51 UTC

−18 points

0 comments2 min readLW link

 Theories of Knowledge

Zero Contradictions11 Aug 2024 8:55 UTC

−1 points

5 comments1 min readLW link

(thewaywardaxolotl.blogspot.com)

Unnatural abstractions

Aprillion10 Aug 2024 22:31 UTC

3 points

3 comments4 min readLW link

(peter.hozak.info)

[LDSL#3] Information-orientation is in tension with magnitude-orientation

tailcalled10 Aug 2024 21:58 UTC

22 points

2 comments3 min readLW link

The AI regulator’s toolbox: A list of concrete AI governance practices

Adam Jones10 Aug 2024 21:15 UTC

7 points

1 comment34 min readLW link

(adamjones.me)

Diffusion Guided NLP: better steering, mostly a good thing

Nathan Helm-Burger10 Aug 2024 19:49 UTC

13 points

0 comments1 min readLW link

(arxiv.org)

Tall tales and long odds

Solenoid_Entity10 Aug 2024 15:22 UTC

11 points

0 comments5 min readLW link

The Great Organism Theory of Evolution

rogersbacon10 Aug 2024 12:26 UTC

20 points

0 comments6 min readLW link

(www.secretorum.life)

Emergence, The Blind Spot of GenAI Interpretability?

Quentin FEUILLADE--MONTIXI10 Aug 2024 10:07 UTC

15 points

8 comments3 min readLW link

Rowing vs steering

Saul Munn10 Aug 2024 7:00 UTC

42 points

2 comments6 min readLW link

(www.brasstacks.blog)

Overpopulation FAQs

Zero Contradictions10 Aug 2024 4:21 UTC

−12 points

7 comments1 min readLW link

(zerocontradictions.net)

Fermi Estimating How Long an Algorithm Takes

SatvikBeri10 Aug 2024 1:34 UTC

1 point

0 comments2 min readLW link

What’s so special about likelihoods?

mfatt10 Aug 2024 1:07 UTC

1 point

0 comments1 min readLW link

Provably Safe AI: Worldview and Projects

bgold and Steve_Omohundro

9 Aug 2024 23:21 UTC

51 points

43 comments7 min readLW link

All The Latest Human tFUS Studies

sarahconstantin9 Aug 2024 22:20 UTC

46 points

2 comments8 min readLW link

(sarahconstantin.substack.com)

But Where do the Variables of my Causal Model come from?

Dalcy9 Aug 2024 22:07 UTC

36 points

1 comment8 min readLW link

[LDSL#2] Latent variable models, network models, and linear diffusion of sparse lognormals

tailcalled9 Aug 2024 19:57 UTC

23 points

2 comments3 min readLW link

“Which Future Mind is Me?” Is a Question of Values

dadadarren9 Aug 2024 18:17 UTC

17 points

12 comments3 min readLW link

Simulation-aware causal decision theory: A case for one-boxing in CDT

kongus_bongus9 Aug 2024 18:09 UTC

15 points

11 comments2 min readLW link

The gatekeepers of the AI algorithms will shape our society

ProfessorFalken9 Aug 2024 17:59 UTC

−5 points

3 comments1 min readLW link

[Question] Practical advice for secure virtual communication post easy AI voice-cloning?

hmys9 Aug 2024 17:32 UTC

6 points

5 comments2 min readLW link

The Carnot Engine of Economics

StrivingForLegibility9 Aug 2024 15:59 UTC

5 points

0 comments5 min readLW link

HVM Superposition Node Program Search Flake

Johannes C. Mayer9 Aug 2024 14:03 UTC

10 points

0 comments1 min readLW link

(github.com)

Outrage Bonding

Jonathan Moregård9 Aug 2024 13:46 UTC

62 points

12 comments2 min readLW link

(honestliving.substack.com)

Non-Transactional Compliments

Jonathan Moregård9 Aug 2024 13:42 UTC

16 points

0 comments1 min readLW link

(honestliving.substack.com)

FarmKind’s Illusory Offer

jefftk9 Aug 2024 11:30 UTC

71 points

5 comments3 min readLW link

(www.jefftk.com)

Altruism and Selfishness

Zero Contradictions9 Aug 2024 6:15 UTC

−3 points

0 comments1 min readLW link

(thewaywardaxolotl.blogspot.com)

Michael Streamlines on Buddhism

Chris_Leong9 Aug 2024 4:44 UTC

8 points

0 comments1 min readLW link

(x.com)

Altruism and Vitalism Aren’t Fellow Travelers

Arjun Panickssery9 Aug 2024 2:01 UTC

24 points

2 comments3 min readLW link

(arjunpanickssery.substack.com)

Caring only about your child may increase human suffering

Cipolla8 Aug 2024 23:47 UTC

−15 points

2 comments8 min readLW link

The Hessian rank bounds the learning coefficient

Lucius Bushnaq8 Aug 2024 20:55 UTC

68 points

9 comments4 min readLW link

GPT-4o System Card

Zach Stein-Perlman8 Aug 2024 20:30 UTC

68 points

11 comments2 min readLW link

(openai.com)

Parasites (not a metaphor)

lemonhope8 Aug 2024 20:07 UTC

122 points

17 comments1 min readLW link

Some Unorthodox Ways To Achieve High GDP Growth

johnswentworth and David Lorell

8 Aug 2024 18:58 UTC

57 points

6 comments6 min readLW link

You can remove GPT2’s LayerNorm by fine-tuning for an hour

StefanHex8 Aug 2024 18:33 UTC

161 points

11 comments8 min readLW link