RSS

Good Reg­u­la­tor Theorems

TagLast edit: 18 Sep 2023 17:09 UTC by abramdemski

The Good Regulator Theorem is a theorem by Roger Conant and W. Ross Ashby which supposedly proves that “every good regulator of a system must be a model of that system”. In fact, there are some problems with that informal characterization.

Fix­ing The Good Reg­u­la­tor Theorem

johnswentworth9 Feb 2021 20:30 UTC
160 points
40 comments8 min readLW link1 review

A Straight­for­ward Ex­pla­na­tion of the Good Reg­u­la­tor Theorem

Alfred Harwood18 Nov 2024 12:45 UTC
91 points
30 comments14 min readLW link

Thoughts on the good reg­u­la­tor theorem

JonasMoss11 Aug 2022 12:08 UTC
12 points
0 comments4 min readLW link

Con­nect­ing the good reg­u­la­tor the­o­rem with se­man­tics and sym­bol grounding

Stuart_Armstrong4 Mar 2021 14:35 UTC
13 points
0 comments2 min readLW link

A Gen­er­al­iza­tion of the Good Reg­u­la­tor Theorem

Alfred Harwood4 Jan 2025 9:55 UTC
21 points
6 comments10 min readLW link

Proof Ex­plained for “Ro­bust Agents Learn Causal World Model”

Dalcy22 Dec 2024 15:06 UTC
28 points
0 comments15 min readLW link

An Illus­trated Sum­mary of “Ro­bust Agents Learn Causal World Model”

Dalcy14 Dec 2024 15:02 UTC
75 points
2 comments10 min readLW link

Align­ment as up­load­ing with more steps

Cole Wyeth14 Sep 2025 4:08 UTC
69 points
33 comments14 min readLW link

[AN #138]: Why AI gov­er­nance should find prob­lems rather than just solv­ing them

Rohin Shah17 Feb 2021 18:50 UTC
12 points
0 comments9 min readLW link
(mailchi.mp)

Some Re­marks on Reg­u­la­tor The­o­rems No One Asked For

Zachary Robertson5 Nov 2021 19:33 UTC
19 points
1 comment4 min readLW link

Re­port & ret­ro­spec­tive on the Dove­tail fellowship

Alex_Altair14 Mar 2025 23:20 UTC
27 points
3 comments9 min readLW link

Limits to the Con­trol­la­bil­ity of AGI

20 Nov 2022 19:18 UTC
11 points
2 comments9 min readLW link

Selec­tion The­o­rems: A Pro­gram For Un­der­stand­ing Agents

johnswentworth28 Sep 2021 5:03 UTC
136 points
28 comments6 min readLW link2 reviews

Search-in-Ter­ri­tory vs Search-in-Map

johnswentworth5 Jun 2021 23:22 UTC
77 points
14 comments4 min readLW link

When bits of op­ti­miza­tion im­ply bits of mod­el­ing: the Touchette-Lloyd theorem

15 Dec 2025 4:21 UTC
32 points
0 comments11 min readLW link

Nat­u­ral Ab­strac­tion: Con­ver­gent Prefer­ences Over In­for­ma­tion Structures

paulom14 Oct 2023 18:34 UTC
28 points
1 comment36 min readLW link

Ab­strac­tion, Causal­ity, and Embed­ded Maps: Here Be Monsters

johnswentworth18 Dec 2019 20:25 UTC
26 points
1 comment4 min readLW link

Book Re­view: Be­ing You by Anil Seth

Alexander26 Oct 2021 5:44 UTC
34 points
23 comments11 min readLW link

Seven ways to Im­prove the In­ter­nal Model Principle

Alfred Harwood17 May 2025 16:38 UTC
15 points
0 comments13 min readLW link

De­cep­tive Align­ment and Homuncularity

16 Jan 2025 13:55 UTC
26 points
12 comments22 min readLW link

In­for­ma­tion-The­o­retic Box­ing of Superintelligences

30 Nov 2023 14:31 UTC
31 points
0 comments7 min readLW link

[Question] Does Agent-like Be­hav­ior Im­ply Agent-like Ar­chi­tec­ture?

Scott Garrabrant23 Aug 2019 2:01 UTC
72 points
9 comments1 min readLW link

Ab­strac­tion, Evolu­tion and Gears

johnswentworth24 Jun 2020 17:39 UTC
29 points
11 comments4 min readLW link

Clar­ify­ing the Agent-Like Struc­ture Problem

johnswentworth29 Sep 2022 21:28 UTC
64 points
19 comments6 min readLW link

The causal back­bone conjecture

tailcalled17 Aug 2024 18:50 UTC
26 points
0 comments2 min readLW link

Do model eval­u­a­tions fall prey to the Good(er) Reg­u­la­tor The­o­rem?

testingthewaters19 Aug 2025 16:19 UTC
6 points
1 comment2 min readLW link

Seth Ex­plains Consciousness

Jacob Falkovich22 Aug 2023 18:06 UTC
39 points
130 comments14 min readLW link1 review
(putanumonit.com)

Disen­tan­gling Com­pe­tence and Intelligence

Robert Kralisch29 Apr 2024 0:12 UTC
23 points
7 comments6 min readLW link

Ex­am­ples of Causal Abstraction

johnswentworth12 Dec 2019 22:54 UTC
24 points
7 comments4 min readLW link

PIBBSS Speaker events com­ings up in February

1 Feb 2024 3:28 UTC
10 points
2 comments1 min readLW link
No comments.