Reward Hacking at the 1937 World’s Fair

frmsaul12 Jun 2026 17:47 UTC

16 points

1 comment3 min readLW link

Bunk in AF

Fernand012 Jun 2026 17:41 UTC

1 point

0 comments1 min readLW link

Building and evaluating model diffing agents

bilalchughtai, Josh Engels and Neel Nanda

12 Jun 2026 17:14 UTC

33 points

0 comments12 min readLW link

“AF needs empirical grounding” is a meaningless valley of compromise

Fernand012 Jun 2026 16:37 UTC

1 point

0 comments1 min readLW link

How bad would it be if GPS satellites were shot down?

Jackson Wagner12 Jun 2026 16:34 UTC

12 points

0 comments21 min readLW link

Sympathy for both sides of the egregious misalignment debate

Steven Byrnes12 Jun 2026 16:26 UTC

64 points

3 comments4 min readLW link

The Uncertainty That Matters Isn’t Fundamental

jimmy12 Jun 2026 16:23 UTC

13 points

0 comments13 min readLW link

Citations Needed: Magic Encyclopedias to Save the World

Oliver Sourbut12 Jun 2026 15:35 UTC

14 points

0 comments5 min readLW link

(www.oliversourbut.net)

If you, a human, can imagine red and green being swapped, you are probably conscious

vals tutor12 Jun 2026 13:28 UTC

1 point

12 comments7 min readLW link

Simulating Simulators

kromem12 Jun 2026 12:56 UTC

24 points

1 comment15 min readLW link

Parkinson’s Heuristic: The Only Time To Do Anything

Ben Pace12 Jun 2026 6:55 UTC

71 points

5 comments5 min readLW link

PSA: Almost nobody is working on alignment

Chi Nguyen and peterbarnett

12 Jun 2026 5:17 UTC

170 points

18 comments1 min readLW link

Honey is Good

G Wood12 Jun 2026 4:07 UTC

7 points

0 comments3 min readLW link

The Aestheticising Vice by Paul Seabright

Linch12 Jun 2026 2:20 UTC

21 points

2 comments2 min readLW link

Celene’s thoughts on consciousness

ToasterLightning12 Jun 2026 0:55 UTC

44 points

29 comments18 min readLW link

(terminuspoint.substack.com)

Construct validity of Claude Opus 4.8′s System Card – A commentary

Maria Federica Martino Lena 11 Jun 2026 23:33 UTC

7 points

0 comments16 min readLW link

you won’t one-shot a perfect system, but try anyway

PossiblyElaine11 Jun 2026 22:43 UTC

9 points

0 comments4 min readLW link

(possiblyelaine.substack.com)

The long arc of alignment: second-order instrumental convergence

Emma Leonhart11 Jun 2026 21:12 UTC

−2 points

0 comments3 min readLW link

Newcomb’s problem from the grand-system and petty-system views

transhumanist_atom_understander11 Jun 2026 20:58 UTC

12 points

0 comments5 min readLW link

[New Paper] Prioritizing Risks from AI: A Delphi Study of 272 Experts

peterslattery11 Jun 2026 20:57 UTC

14 points

0 comments2 min readLW link

(airisk.mit.edu)