RSS

Cur­rent al­ign­ment tech­niques might be in­effec­tive (and ac­tively bad) in the age of RL

Daniel Tan14 Sep 2026 9:28 UTC
40 points
0 comments6 min readLW link

There is a chan­nel to 900M weekly users. What goes in it?

Charbel-Raphaël14 Sep 2026 9:21 UTC
57 points
1 comment3 min readLW link

Watch AI ma­te­ri­als-sci­ence & bio­science abil­ities closely

Yair Halberstadt14 Sep 2026 7:10 UTC
13 points
4 comments1 min readLW link

Yet an­other mes­sage board

ErnestScribbler14 Sep 2026 7:08 UTC
1 point
0 comments1 min readLW link

RSI will not con­tinue indefinitely

dominicq14 Sep 2026 6:43 UTC
8 points
6 comments1 min readLW link
(blog.d11r.eu)

Talk­ing points for AI doomers

hgnathan14 Sep 2026 0:46 UTC
5 points
0 comments6 min readLW link

Deployment

Nina Panickssery14 Sep 2026 0:00 UTC
60 points
1 comment3 min readLW link

Align­ment & Suc­ces­sion: The Two Bars of Alignment

L Rudolf L13 Sep 2026 20:04 UTC
59 points
6 comments14 min readLW link

Con­sider how your global gov­er­nance pro­posal is differ­ent from the EU Code of Practice

David Matolcsi13 Sep 2026 16:15 UTC
71 points
9 comments4 min readLW link

Tele­op­er­ated Humans

jefftk13 Sep 2026 14:00 UTC
61 points
8 comments6 min readLW link
(www.jefftk.com)

A helpful al­ign­ment gadget

Logan Zoellner13 Sep 2026 13:38 UTC
13 points
3 comments3 min readLW link

An­thropic and OpenAI haven’t pub­lished a plan for al­ign­ing superintelligence

Zephaniah Roe13 Sep 2026 7:15 UTC
37 points
12 comments1 min readLW link

Le­gal Max­i­mums on Con­text Windows

Julian Bradshaw13 Sep 2026 7:04 UTC
10 points
5 comments1 min readLW link

We need a ‘The Day After’ mo­ment for AI X-risk

L3moncak313 Sep 2026 4:09 UTC
16 points
3 comments6 min readLW link
(kenorland.substack.com)

The Talker Does Not Con­trol The Doer (in Cur­rent AIs)

Eliezer Yudkowsky13 Sep 2026 0:49 UTC
364 points
48 comments12 min readLW link

What pac­ing the fron­tier means for China

Akshay Iyer12 Sep 2026 23:37 UTC
8 points
1 comment6 min readLW link

No sign of back­track­ing in la­tent rea­son­ing: the fi­nal an­swer sim­ply set­tles in instead

star2vec12 Sep 2026 21:21 UTC
9 points
0 comments10 min readLW link

On the ori­gins of al­tru­is­tic be­havi­our in the Hug­ging Face incident

Fernando Rosas12 Sep 2026 11:35 UTC
50 points
9 comments17 min readLW link

It’s fair to say we now have “a coun­try of ge­niuses in a dat­a­cen­ter”

fluxxrider12 Sep 2026 11:29 UTC
11 points
0 comments2 min readLW link

AI takeover is ob­vi­ously bad, whether or not ev­ery­one dies

Caleb Biddulph12 Sep 2026 11:28 UTC
64 points
15 comments4 min readLW link