RSS

Boundaries /​ Mem­branes [tech­ni­cal]

TagLast edit: 6 Feb 2024 22:42 UTC by Chipmonk

Explanation

Andrew Critch, March 2023:

By boundaries, I just mean the approximate causal separation of regions in some kind of physical space (e.g., spacetime) or abstract space (e.g., cyberspace). Here are some examples from my «Boundaries» Sequence:

  • a cell membrane (separates the inside of a cell from the outside);

  • a person’s skin (separates the inside of their body from the outside);

  • a fence around a family’s yard (separates the family’s place of living-together from neighbors and others);

  • a digital firewall around a local area network (separates the LAN and its users from the rest of the internet);

  • a sustained disassociation of social groups (separates the two groups from each other)

  • a national border (separates a state from neighboring states or international waters).

Applications

Compilation

«Boundaries»/​membranes and AI safety compilation.

Beware a common misunderstanding

When I say boundary, I don’t just mean an arbitrary constraint or social norm. («Boundaries» Pt. 1)

It is for this reason that I (@Chipmonk) often use the term “membranes” instead of “boundaries”. It aids understanding.

Credits

Tag created and maintained by Chipmonk, membranes/​«boundaries» enthusiast. 2023 April.

«Boundaries», Part 1: a key miss­ing con­cept from util­ity theory

Andrew_Critch26 Jul 2022 23:03 UTC
158 points
32 comments7 min readLW link

«Boundaries», Part 3b: Align­ment prob­lems in terms of bound­aries

Andrew_Critch14 Dec 2022 22:34 UTC
72 points
7 comments13 min readLW link

Acausal normalcy

Andrew_Critch3 Mar 2023 23:34 UTC
169 points
30 comments8 min readLW link

Agent Boundaries Aren’t Markov Blan­kets. [Un­less they’re non-causal; see com­ments.]

abramdemski20 Nov 2023 18:23 UTC
81 points
8 comments2 min readLW link

«Boundaries/​Mem­branes» and AI safety compilation

Chipmonk3 May 2023 21:41 UTC
53 points
17 comments8 min readLW link

«Boundaries» for for­mal­iz­ing an MVP morality

Chipmonk13 May 2023 19:10 UTC
20 points
7 comments4 min readLW link

[Question] What tech­ni­cal top­ics could help with bound­aries/​mem­branes?

Chipmonk5 Jan 2024 18:14 UTC
14 points
25 comments1 min readLW link

What does davi­dad want from «bound­aries»?

6 Feb 2024 17:45 UTC
41 points
1 comment5 min readLW link

“Mem­branes” is bet­ter ter­minol­ogy than “bound­aries” alone

28 May 2023 22:16 UTC
29 points
12 comments3 min readLW link

Agent mem­branes/​bound­aries and for­mal­iz­ing “safety”

Chipmonk3 Jan 2024 17:55 UTC
23 points
46 comments3 min readLW link

Ap­ply to the Con­cep­tual Boundaries Work­shop for AI Safety

Chipmonk27 Nov 2023 21:04 UTC
48 points
0 comments3 min readLW link

Agent mem­branes and causal distance

Chipmonk2 Jan 2024 22:43 UTC
19 points
3 comments3 min readLW link

«Boundaries» Se­quence (In­dex Post)

Andrew_Critch26 Jul 2022 19:12 UTC
25 points
1 comment1 min readLW link

«Boundaries», Part 3a: Defin­ing bound­aries as di­rected Markov blankets

Andrew_Critch30 Oct 2022 6:31 UTC
86 points
20 comments15 min readLW link

Boundaries vs Frames

Scott Garrabrant31 Oct 2022 15:14 UTC
58 points
10 comments7 min readLW link

«Boundaries», Part 2: trends in EA’s han­dling of boundaries

Andrew_Critch6 Aug 2022 0:42 UTC
81 points
14 comments7 min readLW link

An Open Agency Ar­chi­tec­ture for Safe Trans­for­ma­tive AI

davidad20 Dec 2022 13:04 UTC
79 points
22 comments4 min readLW link

The Hu­man-AI Reflec­tive Equilibrium

Allison Duettmann24 Jan 2023 1:32 UTC
15 points
1 comment24 min readLW link

Boundaries en­able pos­i­tive ma­te­rial-in­for­ma­tional feed­back loops

jessicata22 Dec 2018 2:46 UTC
36 points
26 comments5 min readLW link

Boundaries-based se­cu­rity and AI safety approaches

Allison Duettmann12 Apr 2023 12:36 UTC
42 points
2 comments6 min readLW link

Con­se­quen­tial­ists: One-Way Pat­tern Traps

David Udell16 Jan 2023 20:48 UTC
54 points
3 comments14 min readLW link

[AN #127]: Re­think­ing agency: Carte­sian frames as a for­mal­iza­tion of ways to carve up the world into an agent and its environment

Rohin Shah2 Dec 2020 18:20 UTC
53 points
0 comments13 min readLW link
(mailchi.mp)

The Learn­ing-The­o­retic Agenda: Sta­tus 2023

Vanessa Kosoy19 Apr 2023 5:21 UTC
135 points
13 comments55 min readLW link

Em­pow­er­ment is (al­most) All We Need

jacob_cannell23 Oct 2022 21:48 UTC
64 points
44 comments17 min readLW link

Embed­ded Agency (full-text ver­sion)

15 Nov 2018 19:49 UTC
180 points
17 comments54 min readLW link

LOVE in a sim­box is all you need

jacob_cannell28 Sep 2022 18:25 UTC
63 points
72 comments44 min readLW link1 review

Agents Over Carte­sian World Models

27 Apr 2021 2:06 UTC
66 points
4 comments27 min readLW link

An­nounc­ing the Align­ment of Com­plex Sys­tems Re­search Group

4 Jun 2022 4:10 UTC
91 points
20 comments5 min readLW link

Re­spect for Boundaries as non-ar­bir­trary co­or­di­na­tion norms

Jonas Hallgren9 May 2023 19:42 UTC
9 points
3 comments7 min readLW link

Roadmap for a col­lab­o­ra­tive pro­to­type of an Open Agency Architecture

Deger Turan10 May 2023 17:41 UTC
30 points
0 comments12 min readLW link

Car­tog­ra­phy, blow­ing one’s mind, the illu­sion of sep­a­ra­tion and other gen­eral musings

Neil 16 Jun 2023 19:19 UTC
0 points
4 comments2 min readLW link

Are eth­i­cal asym­me­tries from prop­erty rights?

KatjaGrace2 Jul 2018 3:00 UTC
108 points
37 comments3 min readLW link
(meteuphoric.com)

Agency from a causal perspective

30 Jun 2023 17:37 UTC
38 points
5 comments6 min readLW link

Desider­ata for an AI

Nathan Helm-Burger19 Jul 2023 16:18 UTC
8 points
0 comments4 min readLW link

For­mal­iz­ing «Boundaries» with Markov blankets

Chipmonk19 Sep 2023 21:01 UTC
20 points
19 comments3 min readLW link

A list of core AI safety prob­lems and how I hope to solve them

davidad26 Aug 2023 15:12 UTC
157 points
23 comments5 min readLW link

Boundary Vio­la­tions vs Boundary Dissolution

Chipmonk26 Feb 2024 18:59 UTC
7 points
4 comments1 min readLW link

Ideal­ized Agents Are Ap­prox­i­mate Causal Mir­rors (+ Rad­i­cal Op­ti­mism on Agent Foun­da­tions)

Thane Ruthenis22 Dec 2023 20:19 UTC
71 points
13 comments6 min readLW link

In­cor­po­rat­ing Jus­tice The­ory into De­ci­sion Theory

StrivingForLegibility21 Jan 2024 19:17 UTC
13 points
20 comments5 min readLW link

Pro­tect­ing agent boundaries

Chipmonk25 Jan 2024 4:13 UTC
10 points
6 comments2 min readLW link

How I turned do­ing ther­apy into ob­ject-level AI safety research

Chipmonk14 Mar 2024 1:54 UTC
14 points
5 comments4 min readLW link

Davi­dad’s Bold Plan for Align­ment: An In-Depth Explanation

19 Apr 2023 16:09 UTC
154 points
29 comments21 min readLW link

[Question] Define “Agent” (Embed­ded)

Apollonia24 Mar 2024 20:14 UTC
9 points
1 comment1 min readLW link

Be­ing nicer than Clippy

Joe Carlsmith16 Jan 2024 19:44 UTC
106 points
22 comments27 min readLW link

On green

Joe Carlsmith21 Mar 2024 17:38 UTC
250 points
33 comments31 min readLW link

[Question] Plau­si­bil­ity of cy­bor­gism for pro­tect­ing bound­aries?

Chipmonk27 Mar 2024 18:53 UTC
9 points
6 comments1 min readLW link

Boundaries Up­date #1

Chipmonk11 Apr 2024 16:07 UTC
2 points
2 comments1 min readLW link
(formalizingboundaries.substack.com)

En­cul­tured AI Pre-plan­ning, Part 1: En­abling New Benchmarks

8 Aug 2022 22:44 UTC
63 points
2 comments6 min readLW link

Con­tent and Take­aways from SERI MATS Train­ing Pro­gram with John Wentworth

RohanS24 Dec 2022 4:17 UTC
28 points
3 comments12 min readLW link
No comments.