In­stan­ti­at­ing an agent with GPT-4 and text-davinci-003

Max H19 Mar 2023 23:57 UTC
13 points
3 comments32 min readLW link

Can This Idea Dra­mat­i­cally Im­prove Effec­tive Ve­gan Ac­tivism?

NothingIsArt19 Mar 2023 23:39 UTC
−5 points
1 comment1 min readLW link

Value Plu­ral­ism and AI

Göran Crafte19 Mar 2023 23:38 UTC
8 points
4 comments2 min readLW link

Ta­boo­ing “Frame Con­trol”

Raemon19 Mar 2023 23:33 UTC
66 points
41 comments10 min readLW link

High Sta­tus Eschews Quan­tifi­ca­tion of Performance

niplav19 Mar 2023 22:14 UTC
126 points
36 comments5 min readLW link

The Hid­den Com­plex­ity of Thought

Isaac King19 Mar 2023 21:59 UTC
15 points
3 comments3 min readLW link
(outsidetheasylum.blog)

[Question] “Wide” vs “Tall” su­per­in­tel­li­gence

Templarrr19 Mar 2023 19:23 UTC
15 points
8 comments1 min readLW link

Hu­man­ity’s Lack of Unity Will Lead to AGI Catastrophe

MiguelDev19 Mar 2023 19:18 UTC
3 points
2 comments4 min readLW link

Prob­a­bil­is­tic Payor Lemma?

abramdemski19 Mar 2023 17:57 UTC
69 points
7 comments4 min readLW link

AGI is un­con­trol­lable, al­ign­ment is impossible

Donatas Lučiūnas19 Mar 2023 17:49 UTC
−12 points
21 comments1 min readLW link

Play­book for the Great Divergence

intellectronica19 Mar 2023 17:42 UTC
14 points
0 comments3 min readLW link
(www.intellectronica.net)

How AI could workaround goals if rated by people

ProgramCrafter19 Mar 2023 15:51 UTC
1 point
1 comment1 min readLW link

[Question] GPT-4 and ASCII Images?

carterallen19 Mar 2023 15:46 UTC
10 points
17 comments1 min readLW link

A ten­sion be­tween two pro­saic al­ign­ment subgoals

Alex Lawsen 19 Mar 2023 14:07 UTC
31 points
8 comments1 min readLW link

Shell games

TsviBT19 Mar 2023 10:43 UTC
85 points
8 comments4 min readLW link

Self-cen­sor­ship is prob­a­bly bad for episte­mol­ogy. Maybe we should figure out a way to avoid it?

DaemonicSigil19 Mar 2023 9:04 UTC
6 points
1 comment3 min readLW link

Mahler 6 at the San Fran­cisco Symphony

yakimoff19 Mar 2023 4:06 UTC
1 point
0 comments1 min readLW link

Fea­ture pro­posal: in­te­grate LessWrong with ChatGPT to pro­mote ac­tive reading

DirectedEvolution19 Mar 2023 3:41 UTC
10 points
4 comments1 min readLW link

Against Deep Ideas

YafahEdelman19 Mar 2023 3:04 UTC
53 points
14 comments2 min readLW link

More in­for­ma­tion about the dan­ger­ous ca­pa­bil­ity eval­u­a­tions we did with GPT-4 and Claude.

Beth Barnes19 Mar 2023 0:25 UTC
233 points
54 comments8 min readLW link
(evals.alignment.org)

Cry­on­ics com­pa­nies should let peo­ple make con­di­tions for reawakening

Andrew Vlahos18 Mar 2023 21:03 UTC
10 points
11 comments4 min readLW link

“Pub­lish or Per­ish” (a quick note on why you should try to make your work leg­ible to ex­ist­ing aca­demic com­mu­ni­ties)

David Scott Krueger (formerly: capybaralet)18 Mar 2023 19:01 UTC
99 points
49 comments1 min readLW link1 review

Dan Luu on “You can only com­mu­ni­cate one top pri­or­ity”

Raemon18 Mar 2023 18:55 UTC
148 points
18 comments3 min readLW link
(twitter.com)

An Ap­peal to AI Su­per­in­tel­li­gence: Rea­sons to Pre­serve Humanity

James_Miller18 Mar 2023 16:22 UTC
37 points
73 comments12 min readLW link

[Question] What did you do with GPT4?

ChristianKl18 Mar 2023 15:21 UTC
27 points
17 comments1 min readLW link

Try to solve the hard parts of the al­ign­ment problem

Mikhail Samin18 Mar 2023 14:55 UTC
54 points
33 comments5 min readLW link

Test­ing ChatGPT 3.5 for poli­ti­cal bi­ases us­ing role­play­ing prompts

twkaiser18 Mar 2023 11:42 UTC
−2 points
2 comments19 min readLW link
(hackernoon.com)

What I did to re­duce the risk of Long COVID (and man­age symp­toms) af­ter get­ting COVID

Sameerishere18 Mar 2023 5:32 UTC
11 points
3 comments10 min readLW link

(re­tired ar­ti­cle) AGI With In­ter­net Ac­cess: Why we won’t stuff the ge­nie back in its bot­tle.

Max TK18 Mar 2023 3:43 UTC
5 points
10 comments4 min readLW link

St. Patty’s Day LA meetup

lc18 Mar 2023 0:00 UTC
8 points
0 comments1 min readLW link

[Question] Why Carl Jung is not pop­u­lar in AI Align­ment Re­search?

MiguelDev17 Mar 2023 23:56 UTC
−3 points
13 comments1 min readLW link

[Event] Join Me­tac­u­lus for Fore­cast Fri­day on March 24th!

ChristianWilliams17 Mar 2023 22:47 UTC
3 points
0 comments1 min readLW link

Meetup Tip: The Next Meetup Will Be. . .

Screwtape17 Mar 2023 22:04 UTC
43 points
0 comments3 min readLW link

The Power of High Speed Stupidity

robotelvis17 Mar 2023 21:41 UTC
33 points
5 comments9 min readLW link
(messyprogress.substack.com)

Ret­ro­spec­tive on ‘GPT-4 Pre­dic­tions’ After the Re­lease of GPT-4

Stephen McAleese17 Mar 2023 18:34 UTC
26 points
6 comments6 min readLW link

“Care­fully Boot­strapped Align­ment” is or­ga­ni­za­tion­ally hard

Raemon17 Mar 2023 18:00 UTC
261 points
22 comments11 min readLW link

[Question] Are nested jailbreaks in­evitable?

judson17 Mar 2023 17:43 UTC
1 point
0 comments1 min readLW link

Eth­i­cal AI in­vest­ments?

Justin wilson17 Mar 2023 17:43 UTC
24 points
15 comments1 min readLW link

New eco­nomic sys­tem for AI era

ksme sho17 Mar 2023 17:42 UTC
−1 points
1 comment5 min readLW link

On some first prin­ci­ples of intelligence

Macheng_Shen17 Mar 2023 17:42 UTC
−14 points
0 comments4 min readLW link

Essen­tial Be­hav­iorism Terms

Rivka17 Mar 2023 17:41 UTC
15 points
1 comment10 min readLW link

Vec­tor se­man­tics and “Kubla Khan,” Part 2

Bill Benzon17 Mar 2023 16:32 UTC
2 points
0 comments3 min readLW link

Su­per-Luigi = Luigi + (Luigi—Waluigi)

Alexei17 Mar 2023 15:27 UTC
16 points
9 comments1 min readLW link

Sur­vey on in­ter­me­di­ate goals in AI governance

17 Mar 2023 13:12 UTC
25 points
3 comments1 min readLW link

GPT-4 solves Gary Mar­cus-in­duced flubs

JakubK17 Mar 2023 6:40 UTC
56 points
29 comments2 min readLW link
(docs.google.com)

[Question] Are the LLM “in­tel­li­gence” tests pub­li­cly available for hu­mans to take?

nim17 Mar 2023 0:09 UTC
7 points
12 comments1 min readLW link

Dona­tion offsets for ChatGPT Plus subscriptions

Jeffrey Ladish16 Mar 2023 23:29 UTC
53 points
3 comments3 min readLW link

The al­gorithm isn’t do­ing X, it’s just do­ing Y.

Cleo Nardo16 Mar 2023 23:28 UTC
53 points
43 comments5 min readLW link

An­nounc­ing the ERA Cam­bridge Sum­mer Re­search Fellowship

Nandini Shiralkar16 Mar 2023 22:57 UTC
11 points
0 comments3 min readLW link

Grad­ual take­off, fast failure

Max H16 Mar 2023 22:02 UTC
15 points
4 comments5 min readLW link