The o1 Sys­tem Card Is Not About o1

ZviDec 13, 2024, 8:30 PM
116 points
5 comments16 min readLW link
(thezvi.wordpress.com)

Arch-an­ar­chy and The Fable of the Dragon-Tyrant

Peter lawless Dec 13, 2024, 8:15 PM
−10 points
0 comments1 min readLW link

Com­mu­ni­ca­tions in Hard Mode (My new job at MIRI)

tanagrabeastDec 13, 2024, 8:13 PM
206 points
25 comments5 min readLW link

First Thoughts on Detachmentism

Jacob PetersonDec 13, 2024, 1:19 AM
−11 points
5 comments9 min readLW link

How to Build Heaven: A Con­strained Boltz­mann Brain Generator

High TidesDec 13, 2024, 1:04 AM
−8 points
3 comments5 min readLW link

Rep­re­sent­ing Ir­ra­tional­ity in Game Theory

Larry LeeDec 13, 2024, 12:50 AM
−1 points
3 comments11 min readLW link

“Char­ity” as a con­fla­tion­ary al­li­ance term

Jan_KulveitDec 12, 2024, 9:49 PM
35 points
2 comments5 min readLW link

Just one more ex­po­sure bro

ChipmonkDec 12, 2024, 9:37 PM
52 points
6 comments2 min readLW link
(chrislakin.blog)

The Dangers of Mir­rored Life

Dec 12, 2024, 8:58 PM
119 points
9 comments29 min readLW link
(www.asimov.press)

Effec­tive Net­work­ing as Send­ing Hard to Fake Signals

vaishnav92Dec 12, 2024, 8:32 PM
26 points
2 comments7 min readLW link
(www.optimaloutliers.com)

Mini PAPR Review

jefftkDec 12, 2024, 7:10 PM
10 points
0 comments2 min readLW link
(www.jefftk.com)

Biolog­i­cal risk from the mir­ror world

jasoncrawfordDec 12, 2024, 7:07 PM
334 points
38 comments7 min readLW link
(newsletter.rootsofprogress.org)

Nat­u­ral­is­tic dualism

Arturo MaciasDec 12, 2024, 4:19 PM
−4 points
0 comments4 min readLW link

AI #94: Not Now, Google

ZviDec 12, 2024, 3:40 PM
49 points
3 comments64 min readLW link
(thezvi.wordpress.com)

Con­scious­ness, In­tel­li­gence, and AI – Some Quick Notes [call it a mini-ram­ble]

Bill BenzonDec 12, 2024, 3:04 PM
−3 points
0 comments4 min readLW link

The Dis­solu­tion of AI Safety

RokoDec 12, 2024, 10:34 AM
8 points
44 comments1 min readLW link
(www.transhumanaxiology.com)

Is Op­ti­miza­tion Cor­rect?

Yoshinori OkamotoDec 12, 2024, 10:27 AM
−9 points
0 comments2 min readLW link

AXRP Epi­sode 38.3 - Erik Jen­ner on Learned Look-Ahead

DanielFilanDec 12, 2024, 5:40 AM
20 points
0 comments16 min readLW link

Public com­put­ers can make ad­dic­tive tools safe

dkl9Dec 11, 2024, 7:55 PM
23 points
0 comments1 min readLW link
(dkl9.net)

Solv­ing New­comb’s Para­dox In Real Life

Alice WanderlandDec 11, 2024, 7:48 PM
3 points
0 comments1 min readLW link
(open.substack.com)

The “Think It Faster” Exercise

RaemonDec 11, 2024, 7:14 PM
144 points
35 comments13 min readLW link

Fore­cast With GiveWell

ChristianWilliamsDec 11, 2024, 5:52 PM
11 points
0 commentsLW link
(www.metaculus.com)

A short­com­ing of con­crete demon­stra­tions as AGI risk advocacy

Steven ByrnesDec 11, 2024, 4:48 PM
105 points
27 comments2 min readLW link

Why Isn’t Tesla Level 3?

jefftkDec 11, 2024, 2:50 PM
22 points
7 comments2 min readLW link
(www.jefftk.com)

In­vest­ing in Ro­bust Safety Mechanisms is crit­i­cal for re­duc­ing Sys­temic Risks

Dec 11, 2024, 1:37 PM
8 points
3 comments2 min readLW link

Post-Quan­tum In­vest­ing: Dump Crypto for In­dex Funds and Real Es­tate?

GDec 11, 2024, 11:59 AM
8 points
5 comments1 min readLW link

Low-effort re­view of “AI For Hu­man­ity”

Charlie SteinerDec 11, 2024, 9:54 AM
13 points
0 comments4 min readLW link

SAEBench: A Com­pre­hen­sive Bench­mark for Sparse Autoencoders

Dec 11, 2024, 6:30 AM
82 points
6 comments2 min readLW link
(www.neuronpedia.org)

Zom­bies! Sub­stance Dual­ist Zom­bies?

Ape in the coatDec 11, 2024, 6:10 AM
15 points
10 comments6 min readLW link

My thoughts on cor­re­la­tion and causation

Victor PortonDec 11, 2024, 5:08 AM
−13 points
3 comments1 min readLW link

Why em­piri­cists should be­lieve in AI risk

Knight LeeDec 11, 2024, 3:51 AM
5 points
0 comments1 min readLW link

[Question] fake al­ign­ment solu­tions????

KvmanThinkingDec 11, 2024, 3:31 AM
1 point
6 comments1 min readLW link

Se­cond-Time Free

jefftkDec 11, 2024, 3:30 AM
24 points
4 comments1 min readLW link
(www.jefftk.com)

Fron­tier AI sys­tems have sur­passed the self-repli­cat­ing red line

aproteinengineDec 11, 2024, 3:06 AM
9 points
4 comments1 min readLW link
(github.com)

The Tech­nist Re­for­ma­tion: A Dis­cus­sion with o1 About The Com­ing Eco­nomic Event Horizon

Yuli_BanDec 11, 2024, 2:34 AM
5 points
2 comments17 min readLW link

LessWrong au­dio: help us choose the new voice

Dec 11, 2024, 2:24 AM
23 points
1 comment1 min readLW link

Ap­ply to at­tend a Global Challenges Pro­ject work­shop in 2025!

LiamEDec 11, 2024, 12:41 AM
6 points
0 comments2 min readLW link
(forum.effectivealtruism.org)

The MVO and The MVP

kwangDec 10, 2024, 11:17 PM
0 points
0 comments7 min readLW link
(kevw.substack.com)

What is Con­fi­dence—in Game The­ory and Life?

James Stephen BrownDec 10, 2024, 11:06 PM
3 points
0 comments8 min readLW link
(nonzerosum.games)

Com­pu­ta­tional func­tion­al­ism prob­a­bly can’t ex­plain phe­nom­e­nal consciousness

EuanMcLeanDec 10, 2024, 5:11 PM
17 points
36 comments12 min readLW link

o1 Turns Pro

ZviDec 10, 2024, 5:00 PM
59 points
3 comments14 min readLW link
(thezvi.wordpress.com)

Most Minds are Irrational

DavidmanheimDec 10, 2024, 9:36 AM
17 points
4 comments10 min readLW link

EC2 Scripts

jefftkDec 10, 2024, 3:00 AM
16 points
1 comment1 min readLW link
(www.jefftk.com)

My Men­tal Model of AI Creativity – Creativity Kiki

Adam NewgasDec 9, 2024, 10:24 PM
12 points
0 comments2 min readLW link
(www.boristhebrave.com)

ACI#9: What is Intelligence

Akira PyinyaDec 9, 2024, 9:54 PM
3 points
0 comments8 min readLW link

The CARLIN Method: Teach­ing AI How to Be Gen­uinely Funny

Greg RobisonDec 9, 2024, 9:51 PM
3 points
0 comments9 min readLW link

o1: A Tech­ni­cal Primer

Jesse HooglandDec 9, 2024, 7:09 PM
170 points
19 comments9 min readLW link
(www.youtube.com)

Cor­rect my H5N1 re­search

ElizabethDec 9, 2024, 7:07 PM
52 points
24 comments2 min readLW link

Re Han­son’s Grabby Aliens: Hu­man­ity is not a nat­u­ral an­thropic sam­ple space

LorecDec 9, 2024, 6:07 PM
14 points
64 comments1 min readLW link

A toy eval­u­a­tion of in­fer­ence code tampering

Fabien RogerDec 9, 2024, 5:43 PM
52 points
0 comments9 min readLW link
(alignment.anthropic.com)