AI ALIGNMENT FORUMTags
AF

Deception

EditHistorySubscribe

Help improve this page (2 flags)

EditHistorySubscribe

Help improve this page (2 flags)

Contributors

1Roman Leventov

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

Posts tagged Deception

0

80Deep Deceptiveness

6mo

16

2

32LCDT, A Myopic Decision Theory

Adam Shimi, Evan Hubinger

2y

44

1

105Model Organisms of Misalignment: The Case for a New Pillar of Alignment Research

Evan Hubinger, Nicholas Schiefer, Carson Denison, Ethan Perez

23d

13

1

49How likely is deceptive alignment?

1y

15

1

20AI Deception: A Survey of Examples, Risks, and Potential Solutions

Simon Goldstein, Peter S. Park

24d

1

1

17The Speed + Simplicity Prior is probably anti-deceptive

[anonymous]1y

6

1

14Precursor checking for deceptive alignment

1y

0

1

40AI x-risk, approximately ordered by embarrassment

5mo

1

1

65Monitoring for deceptive alignment

1y

4

0

34Are minimal circuits deceptive?

4y

9

0

17An Increasingly Manipulative Newsfeed

Michaël Trazzi

4y

1

0

19Will transparency help catch deception? Perhaps not

Matthew Barnett

4y

5

1

21Latent Adversarial Training

1y

2

0

14Plausibly, almost every powerful algorithm would be manipulative

Stuart Armstrong

4y

9

0

14Getting up to Speed on the Speed Prior in 2022

9mo

0