Meta-agentic Prisoner’s Dilemmas

TsviBT5 Nov 2025 16:44 UTC

28 points

0 comments5 min readLW link

Living in the Shadow of The Sort

Gordon Seidoh Worley5 Nov 2025 16:31 UTC

10 points

0 comments5 min readLW link

(www.uncertainupdates.com)

Hardening against AI takeover is difficult, but we should try

otto.barten5 Nov 2025 16:25 UTC

5 points

0 comments5 min readLW link

(www.existentialriskobservatory.org)

ACX Montreal meetup—November 8th @1PM

BionicD0LPH1N5 Nov 2025 14:03 UTC

4 points

0 comments1 min readLW link

AI Safety at the Frontier: Paper Highlights of October 2025

gasteigerjo5 Nov 2025 13:39 UTC

6 points

0 comments8 min readLW link

(aisafetyfrontier.substack.com)

New homepage for AI safety resources – AISafety.com redesign

Bryce Robertson, Søren Elverlin and Melissa Samworth

5 Nov 2025 10:33 UTC

26 points

1 comment1 min readLW link

An atheist’s guide to prayer

Nathan Young5 Nov 2025 9:51 UTC

10 points

1 comment5 min readLW link

(open.substack.com)

Theory of Change for US Govt Whistleblower Database and Guide

samuelshadrach5 Nov 2025 9:08 UTC

2 points

0 comments14 min readLW link

(samuelshadrach.com)

AGI is building itself

Anonim Anonymous5 Nov 2025 8:52 UTC

−8 points

0 comments1 min readLW link

Suffering is what makes it special

Dentosal5 Nov 2025 8:04 UTC

6 points

1 comment2 min readLW link

Maxwell’s Demon and the Arrow of Time

Adam Scherlis5 Nov 2025 7:35 UTC

24 points

1 comment6 min readLW link

(adam.scherl.is)

How to be convincing when talking to people about existential threat from AI

Mikhail Samin5 Nov 2025 7:01 UTC

13 points

2 comments5 min readLW link

Sable and Able: A Tale of Two ASIs

Mr Beastly5 Nov 2025 6:18 UTC

−1 points

0 comments18 min readLW link

Why Safety Constraints in LLMs Are Easily Breakable? Knowledge as a Network of Gated Circuits

Aditya Raj5 Nov 2025 5:20 UTC

6 points

0 comments4 min readLW link

Using math to foster acceptance and equality

jackoda5 Nov 2025 5:16 UTC

1 point

0 comments1 min readLW link

Dario Amodei’s “Machines of Loving Grace” sounds incredibly dangerous, for Humans

Super AGI5 Nov 2025 4:42 UTC

12 points

1 comment1 min readLW link

What are you excited about doing?

mingyuan5 Nov 2025 4:40 UTC

10 points

0 comments2 min readLW link

(mingyuan.substack.com)

Intentionality

abramdemski5 Nov 2025 4:30 UTC

21 points

2 comments2 min readLW link

Food-related things that have made my life a little better

Philipreal5 Nov 2025 3:47 UTC

6 points

1 comment2 min readLW link

Gerrymandering California

Nisan5 Nov 2025 2:46 UTC

13 points

0 comments3 min readLW link