RSS

How to safely use an optimizer

Simon Fischer28 Mar 2024 16:11 UTC
35 points
19 comments7 min readLW link

[Linkpost] Prac­ti­cally-A-Book Re­view: Root­claim $100,000 Lab Leak Debate

trevor28 Mar 2024 16:03 UTC
42 points
6 comments3 min readLW link
(www.astralcodexten.com)

Idea black holes

Logan Kieller28 Mar 2024 15:17 UTC
8 points
1 comment11 min readLW link
(logankieller.substack.com)

Inex­is­tence of Ra­tional Disagree­ment when In­for­ma­tion can be Freely Exchanged

Cheops Steller28 Mar 2024 12:40 UTC
−5 points
2 comments1 min readLW link

AI #57: All the AI News That’s Fit to Print

Zvi28 Mar 2024 11:40 UTC
22 points
3 comments67 min readLW link
(thezvi.wordpress.com)

How do LLMs give truth­ful an­swers? A dis­cus­sion of LLM vs. hu­man rea­son­ing, en­sem­bles & parrots

Owain_Evans28 Mar 2024 2:34 UTC
26 points
0 comments9 min readLW link

UDT1.01: The Story So Far (1/​10)

Diffractor27 Mar 2024 23:22 UTC
18 points
4 comments13 min readLW link

Some Things That In­crease Blood Flow to the Brain

romeostevensit27 Mar 2024 21:48 UTC
24 points
8 comments1 min readLW link

[SP] The Edge of Morality

Zane27 Mar 2024 21:38 UTC
−1 points
2 comments2 min readLW link

The Cog­ni­tive-The­o­retic Model of the Uni­verse: A Par­tial Sum­mary and Review

jessicata27 Mar 2024 19:59 UTC
48 points
11 comments36 min readLW link
(unstablerontology.substack.com)

[Question] Plau­si­bil­ity of cy­bor­gism for pro­tect­ing bound­aries?

Chipmonk27 Mar 2024 18:53 UTC
5 points
2 comments1 min readLW link

Towards White Box Deep Learning

Maciej Satkiewicz27 Mar 2024 18:20 UTC
15 points
4 comments1 min readLW link
(arxiv.org)

Daniel Kah­ne­man has died

DanielFilan27 Mar 2024 15:59 UTC
150 points
6 comments1 min readLW link
(www.washingtonpost.com)

Nick Bostrom’s new book, “Deep Utopia”, is out today

PeterH27 Mar 2024 11:24 UTC
64 points
1 comment1 min readLW link
(nickbostrom.com)

De­com­piling Tracr Trans­form­ers—An in­ter­pretabil­ity experiment

Hannes Thurnherr27 Mar 2024 9:49 UTC
0 points
0 comments14 min readLW link

Some find­ings from train­ing SAEs on Othello-GPT

vlad k27 Mar 2024 9:23 UTC
4 points
0 comments15 min readLW link

Have we re­ally for­saken nat­u­ral se­lec­tion?

KatjaGrace27 Mar 2024 6:50 UTC
14 points
4 comments2 min readLW link
(worldspiritsockpuppet.com)

Robin Han­son and I talk about AI risk

KatjaGrace27 Mar 2024 6:50 UTC
12 points
1 comment1 min readLW link
(worldspiritsockpuppet.com)

20 min­utes of work as an artist in one future

Phib27 Mar 2024 6:49 UTC
10 points
0 comments4 min readLW link

Beauty and the Bets

Ape in the coat27 Mar 2024 6:17 UTC
2 points
13 comments12 min readLW link