“Real sum­mer”?

duck_masterAug 26, 2024, 10:11 PM
2 points
0 comments1 min readLW link

Me­tac­u­lus’s ‘Mini­tac­u­lus’ Ex­per­i­ments — Col­lab­o­rate With Us

ChristianWilliamsAug 26, 2024, 8:44 PM
7 points
0 commentsLW link
(www.metaculus.com)

My Apart­ment Art Com­mis­sion Process

jennAug 26, 2024, 6:36 PM
34 points
4 comments7 min readLW link
(jenn.site)

My (cur­rent) model of what an AI gov­er­nance re­searcher does

Johan de KockAug 26, 2024, 5:58 PM
1 point
2 comments5 min readLW link

Would catch­ing your AIs try­ing to es­cape con­vince AI de­vel­op­ers to slow down or un­de­ploy?

BuckAug 26, 2024, 4:46 PM
316 points
77 comments4 min readLW link

… Wait, our mod­els of se­man­tics should in­form fluid me­chan­ics?!?

Aug 26, 2024, 4:38 PM
59 points
18 comments4 min readLW link

Day Zero An­tivirals for Fu­ture Pandemics

Niko_McCartyAug 26, 2024, 3:18 PM
22 points
2 comments10 min readLW link
(www.asimov.press)

Molec­u­lar dy­nam­ics data will be es­sen­tial for the next gen­er­a­tion of ML pro­tein models

Abhishaike MahajanAug 26, 2024, 2:50 PM
9 points
0 comments11 min readLW link
(www.owlposting.com)

My luke­warm take on GLP-1 agonists

George3d6Aug 26, 2024, 12:34 PM
16 points
0 comments1 min readLW link
(cerebralab.com)

In­ter­view with Robert Kral­isch on Simulators

WillPetilloAug 26, 2024, 5:49 AM
17 points
0 comments75 min readLW link

One per­son’s worth of men­tal en­ergy for AI doom aver­sion jobs. What should I do?

LorecAug 26, 2024, 1:29 AM
9 points
17 comments1 min readLW link

Sec­u­lar in­ter­pre­ta­tions of core peren­ni­al­ist claims

zhukeepaAug 25, 2024, 11:41 PM
83 points
32 comments14 min readLW link

Dar­wi­nian Traps and Ex­is­ten­tial Risks

KristianRonnAug 25, 2024, 10:37 PM
85 points
14 comments10 min readLW link

DIY LessWrong Jewelry

FluffnuttAug 25, 2024, 9:33 PM
33 points
0 comments1 min readLW link

Meta: On view­ing the lat­est LW posts

quiet_NaNAug 25, 2024, 7:31 PM
5 points
2 comments1 min readLW link

you should prob­a­bly eat oat­meal sometimes

bhauthAug 25, 2024, 2:50 PM
41 points
32 comments3 min readLW link
(bhauth.com)

Referen­dum Me­chan­ics in a Mar­ket­place of Ideas

Martin SustrikAug 25, 2024, 8:30 AM
57 points
2 comments5 min readLW link
(250bpm.substack.com)

Please stop us­ing mediocre AI art in your posts

RaemonAug 25, 2024, 12:13 AM
115 points
24 comments2 min readLW link

AXRP Epi­sode 35 - Peter Hase on LLM Beliefs and Easy-to-Hard Generalization

DanielFilanAug 24, 2024, 10:30 PM
21 points
0 comments74 min readLW link

The top 30 books to ex­pand the ca­pa­bil­ities of AI: a bi­ased read­ing list

Jonathan MuganAug 24, 2024, 9:48 PM
−6 points
0 comments16 min readLW link

The Ap Distribution

criticalpointsAug 24, 2024, 9:45 PM
22 points
8 comments3 min readLW link
(eregis.github.io)

What is it to solve the al­ign­ment prob­lem? (Notes)

Joe CarlsmithAug 24, 2024, 9:19 PM
69 points
18 comments53 min readLW link

Ex­am­ine self mod­ifi­ca­tion as an in­tu­ition provider for the con­cept of con­scious­ness

CanalettoAug 24, 2024, 8:48 PM
−4 points
2 comments10 min readLW link

[Question] Look­ing to in­ter­view AI Safety re­searchers for a book

jeffreycarusoAug 24, 2024, 7:57 PM
14 points
0 comments1 min readLW link

Per­plex­ity wins my AI race

ElizabethAug 24, 2024, 7:20 PM
107 points
12 comments10 min readLW link
(acesounderglass.com)

Why should any­one boot *you* up?

onurAug 24, 2024, 5:51 PM
−1 points
5 comments3 min readLW link
(solmaz.io)

Un­der­stand­ing Hid­den Com­pu­ta­tions in Chain-of-Thought Reasoning

rokosbasiliskAug 24, 2024, 4:35 PM
6 points
1 comment1 min readLW link

Au­gust 2024 Time Tracking

jefftkAug 24, 2024, 1:50 PM
22 points
0 comments3 min readLW link
(www.jefftk.com)

Train­ing a Sparse Au­toen­coder in < 30 min­utes on 16GB of VRAM us­ing an S3 cache

Louka Ewington-PitsosAug 24, 2024, 7:39 AM
17 points
0 comments5 min readLW link

[Question] Look­ing for in­tu­itions to ex­tend bar­gain­ing notions

ProgramCrafterAug 24, 2024, 5:00 AM
13 points
0 comments1 min readLW link

Owain Evans on Si­tu­a­tional Aware­ness and Out-of-Con­text Rea­son­ing in LLMs

Michaël TrazziAug 24, 2024, 4:30 AM
55 points
0 comments5 min readLW link

[Question] Devel­op­ing Pos­i­tive Habits through Video Games

pzasAug 24, 2024, 3:47 AM
1 point
5 comments1 min readLW link

“Can AI Scal­ing Con­tinue Through 2030?”, Epoch AI (yes)

gwernAug 24, 2024, 1:40 AM
135 points
4 comments3 min readLW link
(epochai.org)

What’s im­por­tant in “AI for epistemics”?

Lukas FinnvedenAug 24, 2024, 1:27 AM
48 points
0 comments28 min readLW link
(www.forethought.org)

Show­ing SAE La­tents Are Not Atomic Us­ing Meta-SAEs

Aug 24, 2024, 12:56 AM
68 points
10 comments20 min readLW link

Us­ing ide­olog­i­cally-charged lan­guage to get gpt-3.5-turbo to di­s­obey it’s sys­tem prompt: a demo

Milan WAug 24, 2024, 12:13 AM
3 points
0 comments6 min readLW link

Craft­ing Poly­se­man­tic Trans­former Bench­marks with Known Circuits

Aug 23, 2024, 10:03 PM
17 points
0 comments25 min readLW link

[Question] What is an ap­pro­pri­ate sam­ple size when sur­vey­ing billions of data points?

BlakeAug 23, 2024, 9:54 PM
1 point
2 comments1 min readLW link

In­ter­pretabil­ity as Com­pres­sion: Re­con­sid­er­ing SAE Ex­pla­na­tions of Neu­ral Ac­ti­va­tions with MDL-SAEs

Aug 23, 2024, 6:52 PM
42 points
8 comments16 min readLW link

How I started be­liev­ing re­li­gion might ac­tu­ally mat­ter for ra­tio­nal­ity and moral philosophy

zhukeepaAug 23, 2024, 5:40 PM
129 points
41 comments7 min readLW link

[Question] What do you ex­pect AI ca­pa­bil­ities may look like in 2028?

nonzerosumAug 23, 2024, 4:59 PM
9 points
5 comments1 min readLW link

In­vi­ta­tion to lead a pro­ject at AI Safety Camp (Vir­tual Edi­tion, 2025)

Aug 23, 2024, 2:18 PM
17 points
2 comments4 min readLW link

If we solve al­ign­ment, do we die any­way?

Seth HerdAug 23, 2024, 1:13 PM
84 points
130 comments4 min readLW link

What’s go­ing on with Per-Com­po­nent Weight Up­dates?

4gateAug 22, 2024, 9:22 PM
1 point
0 comments6 min readLW link

In­ter­op­er­a­ble High Level Struc­tures: Early Thoughts on Adjectives

Aug 22, 2024, 9:12 PM
49 points
1 comment7 min readLW link

In­ter­est poll: A time-waster blocker for desk­top Linux programs

nahojAug 22, 2024, 8:44 PM
4 points
5 comments1 min readLW link

Turn­ing 22 in the Pre-Apocalypse

testingthewatersAug 22, 2024, 8:28 PM
38 points
14 comments24 min readLW link
(utilityhotbar.github.io)

A Ro­bust Nat­u­ral La­tent Over A Mixed Distri­bu­tion Is Nat­u­ral Over The Distri­bu­tions Which Were Mixed

Aug 22, 2024, 7:19 PM
42 points
4 comments4 min readLW link

what be­com­ing more se­cure did for me

Chris LakinAug 22, 2024, 5:44 PM
26 points
5 comments2 min readLW link
(chrislakin.blog)

A primer on the cur­rent state of longevity research

Abhishaike MahajanAug 22, 2024, 5:14 PM
109 points
6 comments14 min readLW link
(www.owlposting.com)