RSS

Value Drift

TagLast edit: Nov 20, 2024, 9:18 PM by Dakara

Value drift refers to the idea that over time, the values or goals of a person or an AI system can change, often in ways that weren’t originally intended.

For humans, this might happen as life experiences, personal growth, or external influences cause someone’s beliefs to evolve.

For AI, it could occur if the system starts to interpret its goals differently as it learns and interacts with the world.

Schel­ling fences on slip­pery slopes

Scott AlexanderMar 16, 2012, 11:44 PM
611 points
250 comments6 min readLW link

Un­der­stand­ing and avoid­ing value drift

TurnTroutSep 9, 2022, 4:16 AM
48 points
14 comments6 min readLW link

Straight-edge Warn­ing Against Phys­i­cal Intimacy

RaphaëllNov 23, 2020, 9:35 PM
17 points
42 comments5 min readLW link

Let Values Drift

Gordon Seidoh WorleyJun 20, 2019, 8:45 PM
4 points
19 comments8 min readLW link

Would I think for ten thou­sand years?

Stuart_ArmstrongFeb 11, 2019, 7:37 PM
25 points
13 comments1 min readLW link

Pre­dict­ing Parental Emo­tional Changes?

jefftkJul 6, 2022, 1:50 PM
39 points
11 comments2 min readLW link
(www.jefftk.com)

Ma­hatma Arm­strong: CEVed to death.

Stuart_ArmstrongJun 6, 2013, 12:50 PM
33 points
62 comments2 min readLW link

[Question] Is value drift net-pos­i­tive, net-nega­tive, or nei­ther?

MarisaJurczykMay 5, 2019, 2:37 AM
5 points
3 comments1 min readLW link

REACH Meetup – Value Drift

RaemonMay 30, 2018, 4:53 AM
4 points
0 comments1 min readLW link

Up­com­ing sta­bil­ity of values

Stuart_ArmstrongMar 15, 2018, 11:36 AM
15 points
15 comments2 min readLW link

Gandhi, mur­der pills, and men­tal illness

erratioOct 13, 2010, 9:16 AM
34 points
16 comments1 min readLW link

New Hackathon: Ro­bust­ness to dis­tri­bu­tion changes and ambiguity

Charbel-RaphaëlJan 31, 2023, 12:50 PM
12 points
3 comments1 min readLW link
No comments.