Subsystem Alignment

6 Nov 2018 16:16 UTC

LW: 99 AF: 27

(The bibliography for the whole sequence can be found here)

What links here?

Formal Inner Alignment, Prospectus by abramdemski (12 May 2021 19:57 UTC; 95 points)
Clarifying some key hypotheses in AI alignment by Ben Cottier (15 Aug 2019 21:29 UTC; 79 points)
Subagents of Cartesian Frames by Scott Garrabrant (2 Nov 2020 22:02 UTC; 53 points)
Brainstorming positive visions of AI by jungofthewon (7 Oct 2020 16:09 UTC; 48 points)
Embedded Agency via Abstraction by johnswentworth (26 Aug 2019 23:03 UTC; 42 points)
Alignment Newsletter #32 by Rohin Shah (12 Nov 2018 17:20 UTC; 18 points)
Legibility Makes Logical Line-Of-Sight Transitive by StrivingForLegibility (19 Jan 2024 23:39 UTC; 13 points)
When Can Optimization Be Done Safely? by StrivingForLegibility (30 Dec 2023 1:24 UTC; 12 points)
An Ontology for Strategic Epistemology by StrivingForLegibility (28 Dec 2023 22:11 UTC; 9 points)
Rob Bensinger's comment on What Are Some Alternative Approaches to Understanding Agency/Intelligence? by interstice (30 Dec 2020 15:56 UTC; 7 points)
cfoster0's comment on There are no coherence theorems by Dan H (21 Feb 2023 16:58 UTC; 7 points)

6 Nov 2018 16:16 UTC

LW: 99 AF: 27