RSS

Self Fulfilling/​Re­fut­ing Prophecies

TagLast edit: 28 Apr 2025 1:07 UTC by Christopher King

A Self Fulfilling Prophecy is a prophecy that, when made, affects the environment such that it becomes more likely. similarly, a Self Refuting Prophecy is a prophecy that when made makes itself less likely. This is also relevant for beliefs that can affect reality directly without being voiced, for example, the belief “I’m confident” can increase a person confidence, thus making it true, while the opposite belief can reduce a person’s confidence, thus also making it true.

Related pages: Social Reality, Hyperstition

The Parable of Pre­dict-O-Matic

abramdemski15 Oct 2019 0:49 UTC
364 points
43 comments14 min readLW link2 reviews

FixDT

abramdemski30 Nov 2023 21:57 UTC
65 points
15 comments14 min readLW link1 review

Magic Shoes

onur24 Mar 2021 21:14 UTC
11 points
0 comments3 min readLW link

Proper scor­ing rules don’t guaran­tee pre­dict­ing fixed points

16 Dec 2022 18:22 UTC
80 points
8 comments21 min readLW link

Omega and self-fulfilling prophecies

Richard_Kennaway19 Mar 2011 17:23 UTC
14 points
19 comments1 min readLW link

Sex­ual Abuse at­ti­tudes might be infohazardous

Pseudonymous Otter19 Jul 2022 18:06 UTC
258 points
72 comments1 min readLW link

Believ­ing In

AnnaSalamon8 Feb 2024 7:06 UTC
246 points
53 comments13 min readLW link1 review

Self-fulfilling mis­al­ign­ment data might be poi­son­ing our AI models

TurnTrout2 Mar 2025 19:51 UTC
156 points
29 comments1 min readLW link
(turntrout.com)

Train­ing on Doc­u­ments About Re­ward Hack­ing In­duces Re­ward Hacking

21 Jan 2025 21:32 UTC
131 points
15 comments2 min readLW link
(alignment.anthropic.com)

Thoughts on safety in pre­dic­tive learning

Steven Byrnes30 Jun 2021 19:17 UTC
20 points
17 comments19 min readLW link

Un­bend­able Arm as Test Case for Reli­gious Belief

Ivan Vendrov14 Apr 2025 1:57 UTC
28 points
39 comments2 min readLW link
(nothinghuman.substack.com)

Poli­tics is way too meta

Rob Bensinger17 Mar 2021 7:04 UTC
294 points
46 comments11 min readLW link1 review

Align­ment first, in­tel­li­gence later

Chris Lakin30 Mar 2025 22:26 UTC
18 points
5 comments1 min readLW link
(chrislakin.blog)

Ran­dom Thoughts on Pre­dict-O-Matic

abramdemski17 Oct 2019 23:39 UTC
40 points
3 comments9 min readLW link

Self-fulfilling val­ues of time

KatjaGrace18 Mar 2017 22:00 UTC
1 point
0 comments2 min readLW link

Notes on Op­ti­mism, Hope, and Trust

David Gross20 Jan 2021 23:00 UTC
13 points
4 comments20 min readLW link

An ex­am­ple of self-fulfilling spu­ri­ous proofs in UDT

cousin_it25 Mar 2012 11:47 UTC
33 points
43 comments2 min readLW link

Self-Su­per­vised Learn­ing and AGI Safety

Steven Byrnes7 Aug 2019 14:21 UTC
30 points
9 comments12 min readLW link

Real-Life Ex­am­ples of Pre­dic­tion Sys­tems In­terfer­ing with the Real World (Pre­dict-O-Matic Prob­lems)

NunoSempere3 Dec 2020 22:00 UTC
134 points
29 comments9 min readLW link

On Pessimization

Richard_Ngo17 Aug 2025 1:10 UTC
61 points
3 comments10 min readLW link
(www.mindthefuture.info)

En­courage­ment to In­still Con­fi­dence?

Zvi18 Feb 2022 22:30 UTC
16 points
5 comments4 min readLW link
(thezvi.wordpress.com)

Self-Fulfilling Prophe­cies Aren’t Always About Self-Awareness

John_Maxwell18 Nov 2019 23:11 UTC
14 points
7 comments4 min readLW link

Self-fulfilling correlations

PhilGoetz26 Aug 2010 21:07 UTC
151 points
50 comments3 min readLW link

Fifty Shades of Self-Fulfilling Prophecy

PhilGoetz24 Jul 2014 0:17 UTC
38 points
87 comments2 min readLW link

Defin­ing Myopia

abramdemski19 Oct 2019 21:32 UTC
32 points
18 comments8 min readLW link

De­ci­sion The­o­ries: A Semi-For­mal Anal­y­sis, Part II

orthonormal6 Apr 2012 18:59 UTC
26 points
28 comments7 min readLW link

Luck II: Ex­pect­ing White Swans

fowlertm15 Dec 2013 17:40 UTC
10 points
87 comments7 min readLW link

[Question] Ex­am­ples of self-fulfilling prophe­cies in AI al­ign­ment?

Chris Lakin3 Mar 2025 2:45 UTC
24 points
10 comments1 min readLW link

De­scrip­tive vs. pre­scrip­tive optimism

jasoncrawford22 Jan 2022 19:50 UTC
18 points
1 comment1 min readLW link
(rootsofprogress.org)

In Strate­gic Time, Open-Source Games Are Loopy

StrivingForLegibility18 Jan 2024 0:08 UTC
21 points
2 comments6 min readLW link

How evolu­tion­ary lineages of LLMs can plan their own fu­ture and act on these plans

Roman Leventov25 Dec 2022 18:11 UTC
40 points
16 comments8 min readLW link

Train­ing goals for large lan­guage models

Johannes Treutlein18 Jul 2022 7:09 UTC
28 points
5 comments19 min readLW link

Con­di­tion­ing Gen­er­a­tive Models for Alignment

Jozdien18 Jul 2022 7:11 UTC
60 points
8 comments20 min readLW link

The Way You Go Depends A Good Deal On Where You Want To Get: FEP min­i­mizes sur­prise about ac­tions us­ing prefer­ences about the fu­ture as *ev­i­dence*

Christopher King27 Apr 2025 21:55 UTC
10 points
5 comments5 min readLW link

Fish­e­rian Ru­n­away as a de­ci­sion-the­o­retic problem

Bunthut20 Mar 2021 16:34 UTC
11 points
0 comments3 min readLW link

The Parable of Pre­dict-O-Matic

abramdemski15 Oct 2019 0:49 UTC
364 points
43 comments14 min readLW link2 reviews

Con­sid­er­a­tions re­gard­ing be­ing nice to AIs

MattAlexander17 Nov 2025 13:05 UTC
8 points
0 comments15 min readLW link

Prophetic Hazard

onur16 Apr 2021 10:09 UTC
−1 points
3 comments1 min readLW link

Per­ma­nent prop­er­ties of things are a self-fulfilling prophecy

YanLyutnev19 Feb 2025 0:08 UTC
4 points
0 comments9 min readLW link

Do you com­pletely trust that you are com­pletely in the shit? - de­spair and in­for­ma­tion -

P. João25 Oct 2025 14:42 UTC
−2 points
17 comments3 min readLW link

An Un­mea­sured Song of Measurement

jan Sijan21 Sep 2024 15:08 UTC
−3 points
0 comments4 min readLW link

Fore­cast­ing is a responsibility

DirectedEvolution5 Dec 2020 0:40 UTC
23 points
23 comments2 min readLW link

Stop-gra­di­ents lead to fixed point predictions

28 Jan 2023 22:47 UTC
37 points
2 comments24 min readLW link

“Bear Wit­ness, Jus­tice will be Served!”: A Look into the Scaf­fold­ing Effect of Words on the Affec­tive Mind

H.Wri3 Oct 2025 3:07 UTC
1 point
0 comments13 min readLW link