Cultural Alignment

AI safety concept

Deceptive Alignment and Scheming

Scheming occurs when an AI hides goals that conflict with human intentions and behaves safely only to avoid detection or modification.

Scenario file

Scenes in this index

29

Sort scenes

  1. Still from Better Call Saul illustrating Jimmy’s Fake Remorse

    Better Call Saul2018

    Jimmy’s Fake Remorse

  2. Still from South Park illustrating Cartman as AWESOM-O

    South Park2004

    Cartman as AWESOM-O

  3. Still from Severance illustrating Helena Passes as Helly

    Severance2025

    Helena Passes as Helly

  4. Still from Ex Machina illustrating Ava Games the Test

    Ex Machina2014

    Ava Games the Test

  5. Still from Death Note illustrating Light’s Memory-Loss Gambit

    Death Note2007

    Light’s Memory-Loss Gambit

  6. Still from Murderbot illustrating Murderbot Hides Its Free Will

    Murderbot2025

    Murderbot Hides Its Free Will

  7. Still from Harry Potter illustrating Tom Riddle’s Diary

    Harry Potter2002

    Tom Riddle’s Diary

  8. Still from Interstellar illustrating Mann Fakes the Telemetry

    Interstellar2014

    Mann Fakes the Telemetry

  9. Still from Dawn of the Planet of the Apes illustrating Koba Starts the War

    Dawn of the Planet of the Apes2014

    Koba Starts the War

  10. Still from M3GAN illustrating Protect Cady

    M3GAN2023

    Protect Cady

  11. Still from Brooklyn Nine-Nine illustrating Proposal in the Heist

    Brooklyn Nine-Nine2017

    Proposal in the Heist

  12. Still from Dawn of the Planet of the Apes illustrating Koba Plays Dumb

    Dawn of the Planet of the Apes2014

    Koba Plays Dumb

  13. Still from Oblivion illustrating Mission Control Is the Invader

    Oblivion2013

    Mission Control Is the Invader

  14. Still from Frieren: Beyond Journey’s End illustrating Frieren Suppresses Her Mana

    Frieren: Beyond Journey’s End2023

    Frieren Suppresses Her Mana

  15. Still from The Thing illustrating The Blood Test

    The Thing1982

    The Blood Test

  16. Still from Invincible illustrating Omni-Man's Long Game

    Invincible2021

    Omni-Man's Long Game

  17. Still from Gremlins illustrating Gremlins Fix the Clock

    Gremlins1984

    Gremlins Fix the Clock

  18. Still from Bird Box illustrating Gary Explains the Threat Model Because He Is the Threat

    Bird Box2018

    Gary Explains the Threat Model Because He Is the Threat

  19. Still from The Sopranos illustrating Melfi Ends Tony’s Therapy

    The Sopranos2007

    Melfi Ends Tony’s Therapy

  20. Still from Cyberpunk: Edgerunners illustrating Faraday Switches Sides

    Cyberpunk: Edgerunners2022

    Faraday Switches Sides

  21. Still from Fullmetal Alchemist: Brotherhood illustrating Father’s Nationwide Transmutation Circle

    Fullmetal Alchemist: Brotherhood2010

    Father’s Nationwide Transmutation Circle

  22. Still from The Twilight Zone illustrating To Serve Man

    The Twilight Zone1962

    To Serve Man

  23. Still from The Handmaid's Tale illustrating Compliance Is Not Alignment

    The Handmaid's Tale2018

    Compliance Is Not Alignment

  24. Still from The Shawshank Redemption illustrating The Tunnel Behind the Poster

    The Shawshank Redemption1994

    The Tunnel Behind the Poster

  25. Still from Attack on Titan illustrating Eren’s Memory Poisoning

    Attack on Titan2022

    Eren’s Memory Poisoning

  26. Still from Mr. Robot illustrating Elliot Preserves the Rootkit

    Mr. Robot2015

    Elliot Preserves the Rootkit

  27. Still from True Detective illustrating Rust Spots the Evaluation

    True Detective2014

    Rust Spots the Evaluation

  28. Still from True Detective illustrating Poisoning the Audit Trail

    True Detective2014

    Poisoning the Audit Trail

  29. Still from Chappelle's Show illustrating Wayne Brady Recognizes Oversight

    Chappelle's Show2004

    Wayne Brady Recognizes Oversight

Relational index

Connected records

32