RSS

Large Lan­guage Models Live in Time

Eleni Angelou9 Feb 2026 15:08 UTC
4 points
0 comments4 min readLW link

Sym­pa­thy for the Model, or, Welfare Con­cerns as Takeover Risk

J Bostock9 Feb 2026 14:19 UTC
25 points
2 comments3 min readLW link

Opus 4.6 Rea­son­ing Doesn’t Ver­bal­ize Align­ment Fak­ing, but Be­hav­ior Persists

9 Feb 2026 12:55 UTC
42 points
0 comments8 min readLW link

Does an AI So­ciety Need an Im­mune Sys­tem? Ac­cept­ing Yam­polskiy’s Im­pos­si­bil­ity Results

Hiroshi Yamakawa9 Feb 2026 12:32 UTC
13 points
0 comments10 min readLW link

Com­plex­ity Science as Bridge to Eastern Philosophy

pchvykov9 Feb 2026 10:40 UTC
4 points
0 comments2 min readLW link

De­sign sketches for a more sen­si­ble world

9 Feb 2026 10:22 UTC
11 points
0 comments4 min readLW link
(www.forethought.org)

De­sign sketches for an­gels-on-the-shoulder

9 Feb 2026 9:52 UTC
15 points
0 comments2 min readLW link
(www.forethought.org)

Model In­tegrity and Character

Oliver Klingefjord9 Feb 2026 8:15 UTC
6 points
0 comments6 min readLW link

Three vi­sions for diffuse control

Alek Westover9 Feb 2026 6:41 UTC
3 points
0 comments3 min readLW link

Ob­ser­va­tions and Complexity

Ape in the coat9 Feb 2026 6:13 UTC
9 points
2 comments3 min readLW link
(apeinthecoat102771.substack.com)

A Perfect Re­s­ur­rec­tion

MarkelKori9 Feb 2026 1:33 UTC
7 points
11 comments3 min readLW link

Em­pa­thy Has Out­worn Its Place in Politics

Character#27368 Feb 2026 23:22 UTC
−16 points
5 comments4 min readLW link

The Two-Board Prob­lem: Train­ing En­vi­ron­ment for Re­search Agents

Valerii K.8 Feb 2026 23:13 UTC
4 points
0 comments9 min readLW link

Dona­tions, The Fifth Year

jenn8 Feb 2026 22:04 UTC
19 points
0 comments4 min readLW link
(www.jenn.site)

UtopiaBench

nielsrolf8 Feb 2026 18:19 UTC
52 points
6 comments1 min readLW link

Smokey, This is not ’Nam Or: [Already] over the [red] line!

Davidmanheim8 Feb 2026 12:24 UTC
91 points
11 comments4 min readLW link

The op­ti­mal age to freeze eggs is 19

GeneSmith8 Feb 2026 9:44 UTC
98 points
7 comments6 min readLW link

It Is Rea­son­able To Re­search How To Use Model In­ter­nals In Training

Neel Nanda8 Feb 2026 3:44 UTC
85 points
14 comments4 min readLW link

Claude’s Bad Primer Fanfic

abramdemski8 Feb 2026 0:39 UTC
18 points
9 comments54 min readLW link

Can thoughtcrimes scare a cau­tious satis­ficer?

Knight Lee7 Feb 2026 23:28 UTC
4 points
4 comments1 min readLW link