Max Harms

Karma: 789

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

Thoughts on AI 2027

Max HarmsApr 9, 2025, 9:26 PM

210 points

48 comments21 min readLW link

(intelligence.org)

Instrumental vs Terminal Desiderata

Max HarmsJun 26, 2024, 8:57 PM

21 points

0 comments3 min readLW link

Max Harms’s Shortform

Max HarmsJun 13, 2024, 6:19 PM

3 points

1 comment LW link

5. Open Corrigibility Questions

Max HarmsJun 10, 2024, 2:09 PM

30 points

0 comments7 min readLW link

4. Existing Writing on Corrigibility

Max HarmsJun 10, 2024, 2:08 PM

50 points

15 comments106 min readLW link

3b. Formal (Faux) Corrigibility

Max HarmsJun 9, 2024, 5:18 PM

21 points

13 comments17 min readLW link

3a. Towards Formal Corrigibility

Max HarmsJun 9, 2024, 4:53 PM

24 points

2 comments19 min readLW link

2. Corrigibility Intuition

Max HarmsJun 8, 2024, 3:52 PM

67 points

10 comments33 min readLW link

1. The CAST Strategy

Max HarmsJun 7, 2024, 10:29 PM

47 points

19 comments38 min readLW link

0. CAST: Corrigibility as Singular Target

Max HarmsJun 7, 2024, 10:29 PM

147 points

12 comments8 min readLW link