Max Harms

Karma: 1,219

Also known as Raelifin: https://www.lesswrong.com/users/raelifin

Contra Collier on IABIED

Max Harms20 Sep 2025 15:55 UTC

226 points

51 comments20 min readLW link

Thoughts on AI 2027

Max Harms9 Apr 2025 21:26 UTC

222 points

61 comments21 min readLW link

(intelligence.org)

Instrumental vs Terminal Desiderata

Max Harms26 Jun 2024 20:57 UTC

21 points

0 comments3 min readLW link

Max Harms’s Shortform

Max Harms13 Jun 2024 18:19 UTC

3 points

18 comments1 min readLW link

5. Open Corrigibility Questions

Max Harms10 Jun 2024 14:09 UTC

30 points

0 comments7 min readLW link

4. Existing Writing on Corrigibility

Max Harms10 Jun 2024 14:08 UTC

55 points

17 comments106 min readLW link

3b. Formal (Faux) Corrigibility

Max Harms9 Jun 2024 17:18 UTC

26 points

13 comments17 min readLW link

3a. Towards Formal Corrigibility

Max Harms9 Jun 2024 16:53 UTC

24 points

2 comments19 min readLW link

2. Corrigibility Intuition

Max Harms8 Jun 2024 15:52 UTC

69 points

10 comments33 min readLW link

1. The CAST Strategy

Max Harms7 Jun 2024 22:29 UTC

48 points

22 comments38 min readLW link

0. CAST: Corrigibility as Singular Target

Max Harms7 Jun 2024 22:29 UTC

150 points

17 comments8 min readLW link