RSS

AI Safety pro­posal—In­fluenc­ing the su­per­in­tel­li­gence explosion

Morgan22 May 2024 23:31 UTC
0 points
1 comment7 min readLW link

The But­ton (Short Comic)

milanrosko22 May 2024 23:28 UTC
3 points
0 comments1 min readLW link

Im­ple­ment­ing Asi­mov’s Laws of Robotics—How I imag­ine al­ign­ment work­ing.

Joshua Clancy22 May 2024 23:15 UTC
2 points
0 comments11 min readLW link

Higher-Order Forecasts

ozziegooen22 May 2024 21:49 UTC
30 points
0 comments1 min readLW link

A Pos­i­tive Dou­ble Stan­dard—Self-Help Prin­ci­ples Work For In­di­vi­d­u­als Not Populations

James Stephen Brown22 May 2024 21:37 UTC
2 points
2 comments5 min readLW link

A Bi-Mo­dal Brain Model

Johannes C. Mayer22 May 2024 20:10 UTC
9 points
1 comment2 min readLW link

[Question] Should we be con­cerned about eat­ing too much soy?

ChristianKl22 May 2024 12:53 UTC
20 points
2 comments1 min readLW link

Pro­ce­du­ral Ex­ec­u­tive Func­tion, Part 3

DaystarEld22 May 2024 11:58 UTC
15 points
2 comments1 min readLW link

Ci­cadas, An­thropic, and the bilat­eral al­ign­ment problem

kromem22 May 2024 11:09 UTC
17 points
0 comments5 min readLW link

“Which chains-of-thought was that faster than?”

Emrik22 May 2024 8:21 UTC
31 points
1 comment4 min readLW link

ARIA’s Safe­guarded AI grant pro­gram is ac­cept­ing ap­pli­ca­tions for Tech­ni­cal Area 1.1 un­til May 28th

Brendon_Wong22 May 2024 6:54 UTC
10 points
0 comments1 min readLW link
(www.aria.org.uk)

An­thropic an­nounces in­ter­pretabil­ity ad­vances. How much does this ad­vance al­ign­ment?

Seth Herd21 May 2024 22:30 UTC
48 points
4 comments3 min readLW link
(www.anthropic.com)

EIS XIII: Reflec­tions on An­thropic’s SAE Re­search Circa May 2024

scasper21 May 2024 20:15 UTC
114 points
9 comments3 min readLW link

Miti­gat­ing ex­treme AI risks amid rapid progress [Linkpost]

Akash21 May 2024 19:59 UTC
18 points
5 comments4 min readLW link

Helping loved ones with their fi­nances: the why and how of an un­usu­ally im­pact­ful opportunity

Sam Anschell21 May 2024 18:48 UTC
0 points
1 comment1 min readLW link
(forum.effectivealtruism.org)

rough draft on what hap­pens in the brain when you have an insight

Emrik21 May 2024 18:02 UTC
9 points
2 comments1 min readLW link

On Dwarkesh’s Pod­cast with OpenAI’s John Schulman

Zvi21 May 2024 17:30 UTC
65 points
3 comments20 min readLW link
(thezvi.wordpress.com)

[Question] Is delet­ing ca­pa­bil­ities still a rele­vant re­search ques­tion?

tailcalled21 May 2024 13:24 UTC
15 points
1 comment1 min readLW link

My Dat­ing Heuristic

Declan Molony21 May 2024 5:28 UTC
13 points
4 comments2 min readLW link

Scorable Func­tions: A For­mat for Al­gorith­mic Forecasting

ozziegooen21 May 2024 4:14 UTC
26 points
0 comments1 min readLW link