AI ALIGNMENT FORUMTags
AF

Deception

EditHistorySubscribe

Help improve this page (2 flags)

EditHistorySubscribe

Help improve this page (2 flags)

Contributors

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

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

Posts tagged Deception

Most Relevant

2

28LCDT, A Myopic Decision Theory

Adam Shimi, Evan Hubinger

1y

44

1

41How likely is deceptive alignment?

3mo

9

1

17The Speed + Simplicity Prior is probably anti-deceptive[anonymous]7mo

6

1

11Precursor checking for deceptive alignment

4mo

0

1

63Monitoring for deceptive alignment

3mo

3

0

29Are minimal circuits deceptive?

3y

9

0

17An Increasingly Manipulative Newsfeed

Michaël Trazzi

3y

1

0

19Will transparency help catch deception? Perhaps not

Matthew Barnett

3y

5

0

14Plausibly, almost every powerful algorithm would be manipulative

Stuart Armstrong

3y

9

1

17Universality Unwrapped

2y

1

1

15Latent Adversarial Training

5mo

0

1

12Conditioning Generative Models

5mo

8

1

9Training Trace Priors and Speed Priors

5mo

0

1

4Training Trace Priors

5mo

11