RSS

Pre­ma­ture Optimization

jcksanderson22 Sep 2026 17:03 UTC
14 points
0 comments2 min readLW link

The Direc­tion of Science Fiction

Bryan Whys22 Sep 2026 16:38 UTC
−12 points
0 comments2 min readLW link

Modern LLMs have tiny GPTs hid­den in­side them

invertedpassion22 Sep 2026 13:33 UTC
39 points
1 comment5 min readLW link

Con­trol­lable-CoT leads to covert rea­son­ing capabilities

Edward Cant22 Sep 2026 13:04 UTC
15 points
0 comments12 min readLW link

Au­tonomous Ev­i­dence Fac­to­ries: Safe and Use­ful Re­cur­sive Self-Improvement

Adam Chlipala22 Sep 2026 12:28 UTC
7 points
0 comments12 min readLW link

To­tal Safety Trans­parency?

Austin Chen22 Sep 2026 5:39 UTC
25 points
1 comment9 min readLW link
(manifund.substack.com)

Math con­tains a lot of stuff

Warty22 Sep 2026 5:39 UTC
7 points
3 comments2 min readLW link

An opinionated primer on Causal De­ci­sion The­ory (CDT) and Ev­i­den­tial De­ci­sion The­ory (EDT)

Chi Nguyen22 Sep 2026 0:06 UTC
28 points
7 comments8 min readLW link

Acausal in­ter­ac­tions: What they are, why they mat­ter, and what to do about them

Chi Nguyen22 Sep 2026 0:01 UTC
16 points
0 comments3 min readLW link

Story Im­print­ing: AI As­sis­tants Ab­sorb Traits from Hu­man Char­ac­ters They Resemble

Jorio Cocola and Owain_Evans
21 Sep 2026 23:56 UTC
41 points
0 comments11 min readLW link

Why ad­vance au­to­mated sci­en­tific labs rather than slow them?

Master Chief21 Sep 2026 23:02 UTC
4 points
1 comment1 min readLW link

What if not Cir­cuits?

CarolusRenniusVitellius21 Sep 2026 22:39 UTC
108 points
7 comments15 min readLW link

CLT Fea­tures Sup­port Man­i­fold Steer­ing, but Hold Only Par­tial Steer­ing Signal

Anna Marbut21 Sep 2026 21:20 UTC
7 points
0 comments7 min readLW link

Swarm Scaling

Toby_Ord21 Sep 2026 20:30 UTC
146 points
11 comments8 min readLW link

Tur­bu­lence & Frag­ility: Prompt­ing-Based Ex­per­i­ments are Sen­si­tive to Stray De­tails (And other les­sons for new re­searchers.)

Czynski21 Sep 2026 19:04 UTC
12 points
0 comments18 min readLW link

Will AI wipe out the hu­man race?

scout121 Sep 2026 18:47 UTC
−3 points
0 comments6 min readLW link

Align­ment Mid­train­ing Cracks Un­der Pressure

J Bostock, sidbaines, Daniel Tan, draganover, ma-rmartinez and David Africa
21 Sep 2026 16:55 UTC
105 points
9 comments6 min readLW link

We’re not ready for the e/​Acc × Longevity prefer­ence cascade

Jackson Wagner21 Sep 2026 15:21 UTC
38 points
19 comments11 min readLW link

A class of state­ment be­tween con­jec­ture and theorem

Jason Fantl21 Sep 2026 15:18 UTC
33 points
5 comments2 min readLW link

Grat­i­tude and the End of the World

Ephraiem Sarabamoun21 Sep 2026 15:06 UTC
5 points
2 comments1 min readLW link