RSS

The ori­gins of the steam en­g­ine: An es­say with in­ter­ac­tive an­i­mated diagrams

jasoncrawford29 Nov 2023 18:30 UTC
11 points
0 comments1 min readLW link
(rootsofprogress.org)

ChatGPT 4 solved all the gotcha prob­lems I posed that tripped ChatGPT 3.5

VipulNaik29 Nov 2023 18:11 UTC
19 points
1 comment14 min readLW link

“Clean” vs. “messy” goal-di­rect­ed­ness (Sec­tion 2.2.3 of “Schem­ing AIs”)

Joe Carlsmith29 Nov 2023 16:32 UTC
10 points
0 comments11 min readLW link

[Question] Thoughts on tele­trans­porta­tion with copies?

titotal29 Nov 2023 12:56 UTC
11 points
10 comments1 min readLW link

In­tro to Su­per­po­si­tion & Sparse Au­toen­coders (Co­lab ex­er­cises)

CallumMcDougall29 Nov 2023 12:56 UTC
27 points
0 comments2 min readLW link

The 101 Space You Will Always Have With You

Screwtape29 Nov 2023 4:56 UTC
85 points
7 comments6 min readLW link

Trust your in­tu­ition—Kah­ne­man’s book misses the for­est for the trees

mnvr29 Nov 2023 4:37 UTC
−1 points
2 comments2 min readLW link

De­cep­tion Chess: Game #2

Zane29 Nov 2023 2:43 UTC
23 points
12 comments2 min readLW link

Black Box Biology

GeneSmith29 Nov 2023 2:27 UTC
43 points
10 comments2 min readLW link

[Question] What would be the shelf life of nu­clear weapon-se­crecy if nu­clear weapons had not im­me­di­ately been used in com­bat?

Gram Stone29 Nov 2023 0:53 UTC
7 points
1 comment1 min readLW link

Scal­ing laws for dom­i­nant as­surance contracts

jessicata28 Nov 2023 23:11 UTC
23 points
0 comments6 min readLW link
(unstableontology.com)

I’m con­fused about in­nate smell neuroanatomy

Steven Byrnes28 Nov 2023 20:49 UTC
33 points
0 comments7 min readLW link

How to Con­trol an LLM’s Be­hav­ior (why my P(DOOM) went down)

RogerDearnaley28 Nov 2023 19:56 UTC
46 points
21 comments10 min readLW link

Up­date #2 to “Dom­i­nant As­surance Con­tract Plat­form”: EnsureDone

moyamo28 Nov 2023 18:02 UTC
33 points
2 comments1 min readLW link

Ethico­physics II: Poli­tics is the Mind-Savior

MadHatter28 Nov 2023 16:27 UTC
−23 points
4 comments4 min readLW link
(bittertruths.substack.com)

Agen­tic Growth

Logan Kieller28 Nov 2023 15:45 UTC
8 points
0 comments3 min readLW link
(logankieller.substack.com)

AISC pro­ject: How promis­ing is au­tomat­ing al­ign­ment re­search? (liter­a­ture re­view)

Bogdan Ionut Cirstea28 Nov 2023 14:47 UTC
4 points
1 comment1 min readLW link
(docs.google.com)

A day in the life of a mechanis­tic in­ter­pretabil­ity researcher

Bill Benzon28 Nov 2023 14:45 UTC
3 points
3 comments1 min readLW link

Two sources of be­yond-epi­sode goals (Sec­tion 2.2.2 of “Schem­ing AIs”)

Joe Carlsmith28 Nov 2023 13:49 UTC
10 points
0 comments15 min readLW link

Self-Refer­en­tial Prob­a­bil­is­tic Logic Ad­mits the Payor’s Lemma

Yudhister Kumar28 Nov 2023 10:27 UTC
62 points
7 comments4 min readLW link