Truth Ter­mi­nal: A re­con­struc­tion of events

Nov 17, 2024, 11:51 PM
5 points

7 votes

Overall karma indicates overall quality.

1 comment7 min readLW link

Which AI Safety Bench­mark Do We Need Most in 2025?

Nov 17, 2024, 11:50 PM
2 points

2 votes

Overall karma indicates overall quality.

2 comments8 min readLW link

“The Solomonoff Prior is Mal­ign” is a spe­cial case of a sim­pler argument

David MatolcsiNov 17, 2024, 9:32 PM
131 points

59 votes

Overall karma indicates overall quality.

46 comments12 min readLW link

Chess As The Model Game

criticalpointsNov 17, 2024, 7:45 PM
19 points

9 votes

Overall karma indicates overall quality.

0 comments8 min readLW link
(eregis.github.io)

The grass is always greener in the en­vi­ron­ment that shaped your values

Karl FaulksNov 17, 2024, 6:00 PM
8 points

5 votes

Overall karma indicates overall quality.

0 comments3 min readLW link

An­nounc­ing turn­trout.com, my new digi­tal home

TurnTroutNov 17, 2024, 5:42 PM
108 points

52 votes

Overall karma indicates overall quality.

33 comments1 min readLW link
(turntrout.com)

Sec­u­lar Sols­tice Song­book Update

jefftkNov 17, 2024, 5:30 PM
14 points

4 votes

Overall karma indicates overall quality.

2 comments1 min readLW link
(www.jefftk.com)

Ger­many-wide ACX Meetup

Fernand0Nov 17, 2024, 10:08 AM
4 points

4 votes

Overall karma indicates overall quality.

0 comments1 min readLW link

Pro­ject Ad­e­quate: Seek­ing Cofounders/​Funders

LorecNov 17, 2024, 3:12 AM
5 points

9 votes

Overall karma indicates overall quality.

7 comments8 min readLW link

Try­ing Bluesky

jefftkNov 17, 2024, 2:50 AM
26 points

8 votes

Overall karma indicates overall quality.

16 comments1 min readLW link
(www.jefftk.com)

AXRP Epi­sode 38.1 - Alan Chan on Agent Infrastructure

DanielFilanNov 16, 2024, 11:30 PM
12 points

2 votes

Overall karma indicates overall quality.

0 comments14 min readLW link

Cross-con­text ab­duc­tion: LLMs make in­fer­ences about pro­ce­du­ral train­ing data lev­er­ag­ing declar­a­tive facts in ear­lier train­ing data

Sohaib ImranNov 16, 2024, 11:22 PM
36 points

17 votes

Overall karma indicates overall quality.

11 comments14 min readLW link

Why We Wouldn’t Build Aligned AI Even If We Could

SnowyiuNov 16, 2024, 8:19 PM
10 points

11 votes

Overall karma indicates overall quality.

7 comments10 min readLW link

Which evals re­sources would be good?

Marius HobbhahnNov 16, 2024, 2:24 PM
51 points

24 votes

Overall karma indicates overall quality.

4 comments5 min readLW link

OpenAI Email Archives (from Musk v. Alt­man and OpenAI blog)

habrykaNov 16, 2024, 6:38 AM
533 points

255 votes

Overall karma indicates overall quality.

81 comments51 min readLW link

Us­ing Danger­ous AI, But Safely?

habrykaNov 16, 2024, 4:29 AM
17 points

5 votes

Overall karma indicates overall quality.

2 comments43 min readLW link

Ayn Rand’s model of “liv­ing money”; and an up­side of burnout

AnnaSalamonNov 16, 2024, 2:59 AM
236 points

127 votes

Overall karma indicates overall quality.

59 comments5 min readLW link

Fun­da­men­tal Uncer­tainty: Epilogue

Gordon Seidoh WorleyNov 16, 2024, 12:57 AM
10 points

4 votes

Overall karma indicates overall quality.

0 comments1 min readLW link

Mak­ing a con­ser­va­tive case for alignment

Nov 15, 2024, 6:55 PM
208 points

98 votes

Overall karma indicates overall quality.

67 comments7 min readLW link

The Case For Giv­ing To The Shrimp Welfare Project

Bentham's BulldogNov 15, 2024, 4:03 PM
−4 points

14 votes

Overall karma indicates overall quality.

14 comments7 min readLW link

Win/​con­tinue/​lose sce­nar­ios and ex­e­cute/​re­place/​au­dit protocols

BuckNov 15, 2024, 3:47 PM
64 points

16 votes

Overall karma indicates overall quality.

2 comments7 min readLW link

Antonym Heads Pre­dict Se­man­tic Op­po­sites in Lan­guage Models

Jake WardNov 15, 2024, 3:32 PM
3 points

2 votes

Overall karma indicates overall quality.

0 comments5 min readLW link

Propos­ing the Con­di­tional AI Safety Treaty (linkpost TIME)

otto.bartenNov 15, 2024, 1:59 PM
11 points

6 votes

Overall karma indicates overall quality.

9 comments3 min readLW link
(time.com)

A The­ory of Equil­ibrium in the Offense-Defense Balance

Maxwell TabarrokNov 15, 2024, 1:51 PM
25 points

10 votes

Overall karma indicates overall quality.

6 comments2 min readLW link
(www.maximum-progress.com)

Bos­ton Sec­u­lar Sols­tice 2024: Call for Singers and Musicans

jefftkNov 15, 2024, 1:50 PM
22 points

3 votes

Overall karma indicates overall quality.

0 comments1 min readLW link
(www.jefftk.com)

An Un­canny Moat

Adam NewgasNov 15, 2024, 11:39 AM
13 points

6 votes

Overall karma indicates overall quality.

0 comments4 min readLW link
(www.boristhebrave.com)

If I care about mea­sure, choices have ad­di­tional bur­den (+AI gen­er­ated LW-com­ments)

avturchinNov 15, 2024, 10:27 AM
5 points

2 votes

Overall karma indicates overall quality.

11 comments2 min readLW link

What are Emo­tions?

Myles HNov 15, 2024, 4:20 AM
5 points

7 votes

Overall karma indicates overall quality.

13 comments8 min readLW link

The Third Fun­da­men­tal Question

ScrewtapeNov 15, 2024, 4:01 AM
66 points

32 votes

Overall karma indicates overall quality.

7 comments6 min readLW link

Dance Differentiation

jefftkNov 15, 2024, 2:30 AM
14 points

3 votes

Overall karma indicates overall quality.

0 comments1 min readLW link
(www.jefftk.com)

Break­ing be­liefs about sav­ing the world

OxidizeNov 15, 2024, 12:46 AM
−1 points

6 votes

Overall karma indicates overall quality.

3 comments9 min readLW link

Col­lege tech­ni­cal AI safety hackathon ret­ro­spec­tive—Ge­or­gia Tech

yixNov 15, 2024, 12:22 AM
44 points

18 votes

Overall karma indicates overall quality.

2 comments5 min readLW link
(open.substack.com)

Gw­ern Bran­wen in­ter­view on Dwarkesh Pa­tel’s pod­cast: “How an Anony­mous Re­searcher Pre­dicted AI’s Tra­jec­tory”

Said AchmizNov 14, 2024, 11:53 PM
87 points

37 votes

Overall karma indicates overall quality.

0 comments1 min readLW link
(www.dwarkeshpatel.com)

In­ter­nal mu­sic player: phe­nomenol­ogy of earworms

dkl9Nov 14, 2024, 11:29 PM
6 points

3 votes

Overall karma indicates overall quality.

4 comments2 min readLW link
(dkl9.net)

The For­ag­ing (Ex-)Ban­dit [Rule­set & Reflec­tions]

abstractapplicNov 14, 2024, 8:16 PM
27 points

8 votes

Overall karma indicates overall quality.

3 comments2 min readLW link

Seven les­sons I didn’t learn from elec­tion day

Eric NeymanNov 14, 2024, 6:39 PM
97 points

64 votes

Overall karma indicates overall quality.

33 comments13 min readLW link
(ericneyman.wordpress.com)

Effects of Non-Uniform Spar­sity on Su­per­po­si­tion in Toy Models

Shreyans JainNov 14, 2024, 4:59 PM
4 points

5 votes

Overall karma indicates overall quality.

3 comments6 min readLW link

AI #90: The Wall

ZviNov 14, 2024, 2:10 PM
32 points

19 votes

Overall karma indicates overall quality.

8 comments42 min readLW link
(thezvi.wordpress.com)

Evolu­tion­ary prompt op­ti­miza­tion for SAE fea­ture visualization

Nov 14, 2024, 1:06 PM
22 points

12 votes

Overall karma indicates overall quality.

0 comments9 min readLW link

AXRP Epi­sode 38.0 - Zhijing Jin on LLMs, Causal­ity, and Multi-Agent Systems

DanielFilanNov 14, 2024, 7:00 AM
14 points

4 votes

Overall karma indicates overall quality.

0 comments12 min readLW link

Fron­tierMath: A Bench­mark for Eval­u­at­ing Ad­vanced Math­e­mat­i­cal Rea­son­ing in AI

TamayNov 14, 2024, 6:13 AM
33 points

12 votes

Overall karma indicates overall quality.

0 comments3 min readLW link
(epoch.ai)

Con­crete Meth­ods for Heuris­tic Es­ti­ma­tion on Neu­ral Networks

Oliver DanielsNov 14, 2024, 5:07 AM
33 points

11 votes

Overall karma indicates overall quality.

0 comments27 min readLW link

Here­sies in the Shadow of the Sequences

Cole WyethNov 14, 2024, 5:01 AM
19 points

16 votes

Overall karma indicates overall quality.

12 comments2 min readLW link

Thoughts af­ter the Wolfram and Yud­kowsky discussion

TahpNov 14, 2024, 1:43 AM
25 points

14 votes

Overall karma indicates overall quality.

13 comments6 min readLW link

Neutrality

sarahconstantinNov 13, 2024, 11:10 PM
160 points

84 votes

Overall karma indicates overall quality.

27 comments11 min readLW link
(sarahconstantin.substack.com)

Anvil Shortage

ScrewtapeNov 13, 2024, 10:57 PM
93 points

52 votes

Overall karma indicates overall quality.

16 comments4 min readLW link

[Question] Us­ing hex to get mur­der ad­vice from GPT-4o

Laurence FreemanNov 13, 2024, 6:30 PM
10 points

11 votes

Overall karma indicates overall quality.

5 comments6 min readLW link

Con­fronting the le­gion of doom.

Spiritus DeiNov 13, 2024, 5:03 PM
−20 points

9 votes

Overall karma indicates overall quality.

3 comments5 min readLW link

Is Deep Learn­ing Ac­tu­ally Hit­ting a Wall? Eval­u­at­ing Ilya Sutskever’s Re­cent Claims

garrisonNov 13, 2024, 5:00 PM
84 points

44 votes

Overall karma indicates overall quality.

14 comments8 min readLW link
(garrisonlovely.substack.com)

MIT Fu­tureTech are hiring ‍a Product and Data Vi­su­al­iza­tion Designer

peterslatteryNov 13, 2024, 2:48 PM
2 points

1 vote

Overall karma indicates overall quality.

0 comments4 min readLW link