AI ALIGNMENT FORUMTags
AF

Deception

Help improve this page (2 flags)

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

2mo

16

2

32LCDT, A Myopic Decision Theory

Adam Shimi, Evan Hubinger

2y

44

1

48How likely is deceptive alignment?

9mo

13

1

17The Speed + Simplicity Prior is probably anti-deceptive[anonymous]1y

6

1

14Precursor checking for deceptive alignment

10mo

0

1

39AI x-risk, approximately ordered by embarrassment

2mo

1

1

64Monitoring for deceptive alignment

9mo

4

0

31Are 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

0

14Plausibly, almost every powerful algorithm would be manipulative

Stuart Armstrong

3y

9

0

14Getting up to Speed on the Speed Prior in 2022

5mo

0

1

18Latent Adversarial Training

1y

2

1

16Universality Unwrapped

3y

1

1

12Conditioning Generative Models

1y

8