RSS

Max Harms

Karma: 1,580

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

Se­ri­ous Flaws in CAST

Max Harms19 Nov 2025 17:27 UTC
105 points
10 comments8 min readLW link

AI Cor­rigi­bil­ity De­bate: Max Harms vs. Jeremy Gillen

Liron, Max Harms and Jeremy Gillen
14 Nov 2025 4:09 UTC
46 points
1 comment75 min readLW link
(doomdebates.com)

Wor­lds Where Iter­a­tive De­sign Suc­ceeds?

Max Harms23 Oct 2025 22:14 UTC
23 points
5 comments8 min readLW link

Any cor­rigi­bil­ity naysay­ers out­side of MIRI?

Max Harms22 Oct 2025 21:26 UTC
28 points
24 comments1 min readLW link

Con­tra Col­lier on IABIED

Max Harms20 Sep 2025 15:55 UTC
235 points
51 comments20 min readLW link

Thoughts on AI 2027

Max Harms9 Apr 2025 21:26 UTC
223 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
31 comments1 min readLW link

5. Open Cor­rigi­bil­ity Questions

Max Harms10 Jun 2024 14:09 UTC
31 points
0 comments7 min readLW link

4. Ex­ist­ing Writ­ing on Corrigibility

Max Harms10 Jun 2024 14:08 UTC
64 points
19 comments106 min readLW link

3b. For­mal (Faux) Corrigibility

Max Harms9 Jun 2024 17:18 UTC
26 points
19 comments17 min readLW link

3a. Towards For­mal Corrigibility

Max Harms9 Jun 2024 16:53 UTC
28 points
2 comments19 min readLW link

2. Cor­rigi­bil­ity Intuition

Max Harms8 Jun 2024 15:52 UTC
74 points
10 comments33 min readLW link

1. The CAST Strategy

Max Harms7 Jun 2024 22:29 UTC
57 points
24 comments38 min readLW link

0. CAST: Cor­rigi­bil­ity as Sin­gu­lar Target

Max Harms7 Jun 2024 22:29 UTC
156 points
19 comments9 min readLW link