Com­mu­nity norms poll (2 mins)

Nathan YoungMar 7, 2024, 9:45 PM
11 points
1 comment1 min readLW link

An­nounc­ing Con­ver­gence Anal­y­sis: An In­sti­tute for AI Sce­nario & Gover­nance Research

Mar 7, 2024, 9:37 PM
23 points
1 comment4 min readLW link

Woods’ new preprint on ob­ject permanence

Steven ByrnesMar 7, 2024, 9:29 PM
58 points
1 comment6 min readLW link

MATS AI Safety Strat­egy Curriculum

Mar 7, 2024, 7:59 PM
74 points
2 comments16 min readLW link

Poli­ti­cal Bi­ases in LLMs: Liter­a­ture Re­view & Cur­rent Uses of AI in Elections

Mar 7, 2024, 7:17 PM
6 points
0 comments6 min readLW link

Ev­i­den­tial Cor­re­la­tions are Sub­jec­tive, and it might be a problem

Martín SotoMar 7, 2024, 6:37 PM
26 points
6 comments14 min readLW link

AI Safety 101 : Ca­pa­bil­ities—Hu­man Level AI, What? How? and When?

Mar 7, 2024, 5:29 PM
46 points
8 comments54 min readLW link

A Re­view of Weak to Strong Gen­er­al­iza­tion [AI Safety Camp]

sevdeawesomeMar 7, 2024, 5:16 PM
14 points
0 comments9 min readLW link

AISN #32: Mea­sur­ing and Re­duc­ing Hazardous Knowl­edge in LLMs Plus, Fore­cast­ing the Fu­ture with LLMs, and Reg­u­la­tory Markets

Mar 7, 2024, 4:39 PM
8 points
0 comments8 min readLW link
(newsletter.safe.ai)

AI #54: Claud­ing Along

ZviMar 7, 2024, 4:00 PM
45 points
11 comments51 min readLW link
(thezvi.wordpress.com)

Be­ing In­ter­ested in Other People

Jonathan MoregårdMar 7, 2024, 10:13 AM
14 points
1 comment3 min readLW link
(youbutbetter.substack.com)

Talk­ing to Congress: Can con­stituents con­tact­ing their leg­is­la­tor in­fluence policy?

Tristan WilliamsMar 7, 2024, 9:24 AM
14 points
0 commentsLW link

Ex­plain­ing the AI Align­ment Prob­lem to Ti­be­tan Bud­dhist Monks

Paul CologneseMar 7, 2024, 9:00 AM
20 points
3 comments6 min readLW link

What if Align­ment is Not Enough?

WillPetilloMar 7, 2024, 8:10 AM
15 points
46 comments9 min readLW link

Sparks of AGI prompts on GPT2XL and its var­i­ant, RLLMv3

MiguelDevMar 7, 2024, 6:33 AM
4 points
0 comments4 min readLW link

An AI, a box, and a threat

jwfiredragonMar 7, 2024, 6:15 AM
9 points
0 comments6 min readLW link

Mud and De­s­pair (Part 4 of “The Sense Of Phys­i­cal Ne­ces­sity”)

LoganStrohlMar 7, 2024, 12:14 AM
38 points
0 comments2 min readLW link

in­tro­duc­tion to ther­mal con­duc­tivity and noise management

bhauthMar 6, 2024, 11:14 PM
31 points
1 comment4 min readLW link
(www.bhauth.com)

Es­say­ing Other Plans

ScrewtapeMar 6, 2024, 10:59 PM
29 points
4 comments7 min readLW link

In­vest in ACX Grants pro­jects!

Saul MunnMar 6, 2024, 8:27 PM
23 points
1 commentLW link

Vote on An­thropic Topics to Discuss

Ben PaceMar 6, 2024, 7:43 PM
75 points
55 comments1 min readLW link

Sim­ple Kelly bet­ting in pre­dic­tion markets

jessicataMar 6, 2024, 6:59 PM
38 points
3 comments3 min readLW link
(unstablerontology.substack.com)

On Claude 3.0

ZviMar 6, 2024, 6:50 PM
76 points
5 comments31 min readLW link
(thezvi.wordpress.com)

[Question] Why cor­re­la­tion, though?

numpyNaNMar 6, 2024, 4:53 PM
22 points
7 comments1 min readLW link

Us­ing axis lines for good or evil

dynomightMar 6, 2024, 2:47 PM
151 points
39 comments4 min readLW link
(dynomight.net)

Let’s build definitely-not-con­scious AI

lemonhopeMar 6, 2024, 7:50 AM
4 points
18 comments1 min readLW link

Movie posters

KatjaGraceMar 6, 2024, 6:20 AM
40 points
0 comments2 min readLW link
(worldspiritsockpuppet.com)

We In­spected Every Head In GPT-2 Small us­ing SAEs So You Don’t Have To

Mar 6, 2024, 5:03 AM
63 points
0 comments12 min readLW link

[Question] Does any­one know good es­says on how differ­ent AI timelines will af­fect as­set prices?

Tim LiptrotMar 6, 2024, 4:21 AM
8 points
2 comments1 min readLW link

Twin Cities ACX Meetup—March 2024

Timothy M.Mar 5, 2024, 9:15 PM
1 point
0 comments1 min readLW link

My Clients, The Liars

ymeskhoutMar 5, 2024, 9:06 PM
247 points
86 comments7 min readLW link

If Ukraine fails, the world will reap fatal consequences

Danylo ZhyrkoMar 5, 2024, 7:42 PM
−22 points
14 comments5 min readLW link

Mak­ing Con­nec­tions with ChatGPT: The Mack­sey Game

Bill BenzonMar 5, 2024, 6:15 PM
5 points
2 comments11 min readLW link

[Question] Good tax­onomies of all risks (small or large) from AI?

Aryeh EnglanderMar 5, 2024, 6:15 PM
6 points
1 comment1 min readLW link

[Question] Mak­ing 2023 ACX Pre­dic­tion Re­sults Public

LegionnaireMar 5, 2024, 5:56 PM
3 points
9 comments1 min readLW link

So­cial sta­tus part 2/​2: ev­ery­thing else

Steven ByrnesMar 5, 2024, 4:29 PM
65 points
2 comments23 min readLW link

So­cial sta­tus part 1/​2: ne­go­ti­a­tions over ob­ject-level preferences

Steven ByrnesMar 5, 2024, 4:29 PM
118 points
15 comments21 min readLW link

Two Tales of AI Takeover: My Doubts

Violet HourMar 5, 2024, 3:51 PM
30 points
8 comments29 min readLW link

Re­search Re­port: Sparse Au­toen­coders find only 9/​180 board state fea­tures in OthelloGPT

Robert_AIZIMar 5, 2024, 1:55 PM
61 points
24 comments10 min readLW link
(aizi.substack.com)

Read the Roon

ZviMar 5, 2024, 1:50 PM
136 points
6 comments19 min readLW link
(thezvi.wordpress.com)

In defense of an­throp­i­cally up­dat­ing EDT

Anthony DiGiovanniMar 5, 2024, 6:21 AM
18 points
17 comments13 min readLW link

Claude Doesn’t Want to Die

garrisonMar 5, 2024, 6:00 AM
22 points
3 commentsLW link
(garrisonlovely.substack.com)

Many ar­gu­ments for AI x-risk are wrong

TurnTroutMar 5, 2024, 2:31 AM
162 points
87 comments12 min readLW link

Some ways of spend­ing your time are bet­ter than others

depressurizeMar 4, 2024, 11:21 PM
6 points
5 comments4 min readLW link

Claude 3 claims it’s con­scious, doesn’t want to die or be modified

Mikhail SaminMar 4, 2024, 11:05 PM
80 points
117 comments14 min readLW link

Mod­ify­ing Jones’ “AI Dilemma” Model

harsimonyMar 4, 2024, 9:55 PM
7 points
0 comments6 min readLW link
(splittinginfinity.substack.com)

Benefits of adding poi­son to your DMT

George3d6Mar 4, 2024, 8:35 PM
6 points
2 comments5 min readLW link
(morelucid.substack.com)

Notes on Awe

David GrossMar 4, 2024, 8:23 PM
20 points
1 comment33 min readLW link

Bos­ton’s Line 1

jefftkMar 4, 2024, 7:30 PM
12 points
0 comments1 min readLW link
(www.jefftk.com)

An­thropic re­lease Claude 3, claims >GPT-4 Performance

LawrenceCMar 4, 2024, 6:23 PM
115 points
41 comments2 min readLW link
(www.anthropic.com)