Sean Herrington

Karma: 738

I have signed no contracts or agreements whose existence I cannot mention.

Independent AI safety researcher currently funding my work by facilitating for BlueDot, but open to other opportunities. Participated in ARENA 6.0, AISC 9 and am a project lead for AISC 10. Happy to collaborate with anyone on the site, especially if it lowers our collective likelihood of death.

We made a map of the doom debate

Sean Herrington, Paul Hindoian, mikaelacankosyan, David Bravo, keivnc, Josh Tuffy, Khai Tran, Maryam Hampaei and Christopher A. Davis

22 May 2026 23:24 UTC

40 points

9 comments6 min readLW link

How to get better at chess (and everything else)

Sean Herrington7 May 2026 11:17 UTC

11 points

0 comments3 min readLW link

(www.chess.com)

Inkhaven, the 548th metapost

Sean Herrington1 May 2026 6:49 UTC

1 point

1 comment3 min readLW link

A Pecking Order Problem

Sean Herrington28 Apr 2026 6:35 UTC

11 points

0 comments2 min readLW link

How to run from a bull

Sean Herrington16 Apr 2026 6:19 UTC

15 points

0 comments4 min readLW link

Ranking inkhaven bloggers: Update

Sean Herrington15 Apr 2026 6:24 UTC

10 points

0 comments3 min readLW link

Some AI threats people aren’t thinking about

Sean Herrington14 Apr 2026 3:47 UTC

12 points

0 comments4 min readLW link

Your body is not a white box (and you’re thinking about weight loss wrong)

Sean Herrington13 Apr 2026 5:22 UTC

16 points

5 comments7 min readLW link

Eating meat is fine if you live in a simulation

Sean Herrington11 Apr 2026 21:32 UTC

5 points

2 comments2 min readLW link

Getting Claude to rank the inkhaven bloggers

Sean Herrington11 Apr 2026 2:38 UTC

24 points

0 comments5 min readLW link

AI identity is not tied to its model

Sean Herrington10 Apr 2026 4:07 UTC

24 points

10 comments2 min readLW link

Stockfish is not a chess superintelligence (and it doesn’t need to be)

Sean Herrington9 Apr 2026 4:29 UTC

26 points

6 comments2 min readLW link

Most people can’t juggle one ball

Sean Herrington8 Apr 2026 0:29 UTC

66 points

10 comments7 min readLW link

Contra Nina Panickssery on advice for children

Sean Herrington6 Apr 2026 21:41 UTC

56 points

4 comments3 min readLW link

Estimates of the expected utility gain of AI Safety Research

Sean Herrington6 Apr 2026 4:19 UTC

13 points

2 comments2 min readLW link

Changes to an optimised thing make it worse

Sean Herrington5 Apr 2026 1:21 UTC

4 points

0 comments2 min readLW link

How to emotionally grasp the risks of AI Safety

Sean Herrington4 Apr 2026 3:34 UTC

23 points

1 comment1 min readLW link

Treat your subconscious like a dog

Sean Herrington3 Apr 2026 1:00 UTC

9 points

5 comments3 min readLW link

The quest for general intelligence is hitting a wall [April Fool’s]

Sean Herrington2 Apr 2026 5:16 UTC

58 points

0 comments2 min readLW link

METR have released Time Horizons 1.1

Sean Herrington3 Feb 2026 19:48 UTC

33 points

0 comments1 min readLW link

(metr.org)