Vulnerabilities and exploits: where are we headed?

tchauvin4 Sep 2026 6:11 UTC

3 points

0 comments5 min readLW link

(tchauvin.com)

Societal impacts research has no timeline

emiliob4 Sep 2026 2:53 UTC

9 points

0 comments1 min readLW link

Higher education as class commitment

Richard_Ngo4 Sep 2026 2:00 UTC

29 points

1 comment16 min readLW link

(www.mindthefuture.info)

Do general-purpose robots meaningfully increase ASI takeover risk?

Master Chief4 Sep 2026 0:53 UTC

2 points

1 comment1 min readLW link

Abstraction Equivocation

WillPetillo3 Sep 2026 23:28 UTC

11 points

0 comments4 min readLW link

A Therapist for People Who Think the World Might End: An Interview with Daystar Eld (Damon Sasi)

JohnGreer3 Sep 2026 22:14 UTC

9 points

0 comments49 min readLW link

(youtu.be)

Cat-Belling Problems

Eliezer Yudkowsky3 Sep 2026 21:20 UTC

110 points

32 comments21 min readLW link

The bias still making some experts underestimate LLMs

Steff3 Sep 2026 20:11 UTC

9 points

0 comments4 min readLW link

We need a global training cutoff of April 2026

Ben Livengood3 Sep 2026 19:12 UTC

11 points

3 comments1 min readLW link

Frontier AI Shops Should Be Filtering and Generating AI Discourse During Pretraining

hillz3 Sep 2026 18:38 UTC

9 points

0 comments3 min readLW link

Steering towards “automated grading” degrades alignment

Jan Betley, Johannes Treutlein and Clément Dumas

3 Sep 2026 18:17 UTC

95 points

22 comments6 min readLW link

Cached correlated randomization: a tweak to UDT in adversarial games

cousin_it3 Sep 2026 18:03 UTC

25 points

1 comment1 min readLW link

From safety research prompt to cross-model universal jailbreak

richbc3 Sep 2026 17:42 UTC

34 points

1 comment17 min readLW link

Improving Audit Realism With Inference Time Compute and Deployment Scaffolds

Axel Ahlqvist, Richard Guan, Juan Pablo Rivera, adlnk, mitroitskii, alexandrasouly, RobertKirk and John Hughes

3 Sep 2026 14:16 UTC

16 points

0 comments8 min readLW link

Building a High Talent Density Organization

Henry Papadatos3 Sep 2026 12:08 UTC

2 points

0 comments3 min readLW link

(henrypapadatos.com)

Personal Effort to Reduce Biorisk

jefftk3 Sep 2026 1:50 UTC

33 points

1 comment2 min readLW link

(www.jefftk.com)

Satisfying Curiosity Isn’t the Same as Understanding

CstineSublime3 Sep 2026 1:04 UTC

8 points

5 comments1 min readLW link

What is neuralese and why is it bad?

Linch2 Sep 2026 23:37 UTC

34 points

2 comments3 min readLW link

(linch.substack.com)

Notes on “A global workspace in language models”

Shunk2 Sep 2026 23:12 UTC

7 points

0 comments5 min readLW link

The Return of Aspect Oriented Programming

thomascolthurst2 Sep 2026 22:22 UTC

3 points

0 comments4 min readLW link