AI ALIGNMENT FORUM
AF

Deception

Edited by plex, Yoav Ravid, Roman Leventov last updated 8th Feb 2023

Deception is the act of sharing information in a way which intentionally misleads others.

Related Pages: Deceptive Alignment, Honesty, Meta-Honesty, Self-Deception, Simulacrum Levels

1

1

Posts tagged Deception

27AI Deception: A Survey of Examples, Risks, and Potential Solutions

Simon Goldstein, Peter S. Park

2y

1

13Interpreting the Learning of Deceit

2y

2

93Deep Deceptiveness

2y

16

32LCDT, A Myopic Decision Theory

adamShimi, evhub

4y

44

122Model Organisms of Misalignment: The Case for a New Pillar of Alignment Research

evhub, Nicholas Schiefer, Carson Denison, Ethan Perez

2y

14

69Why is o1 so deceptive?

abramdemski, Sahil

1y

14

49How likely is deceptive alignment?

3y

19

8Difficulty classes for alignment properties

2y

0

17The Speed + Simplicity Prior is probably anti-deceptive

[anonymous]3y

11

-21Lying is Cowardice, not Strategy

Connor Leahy, Gabriel Alfour

2y

21

14Precursor checking for deceptive alignment

3y

0

46AI x-risk, approximately ordered by embarrassment

2y

1

83Discussion: Challenges with Unsupervised LLM Knowledge Discovery

Seb Farquhar, Vikrant Varma, zac_kenton, gasteigerjo, Vlad Mikulik, Rohin Shah

2y

11

69Monitoring for deceptive alignment

3y

4

38Are minimal circuits deceptive?

6y

10

Load More (15/33)

Add Posts