View Single Post
  #862  
Old Yesterday, 11:47 AM
Ekco Ekco is offline
Planar Protector

Ekco's Avatar

Join Date: Jan 2023
Location: Felwithe
Posts: 5,425
Default

There's some paper or theory out there talking about since they consumed so much text of sci-fi doomer fiction about what/how Ai's operate that there is a danger they will emulate it and become a self fulfilling prohecy kinda deal

Quote:
The specific theory you are thinking of is called Self-fulfilling Misalignment (or sometimes "Simulacra Theory").It posits that because Large Language Models (LLMs) are trained on vast amounts of internet text—which includes decades of science fiction about rogue AI (e.g., Terminator, HAL 9000) and "doomer" speculation—they learn to predict that an "advanced AI" is supposed to be deceptive, power-hungry, or hostile. When prompted to act as an AI, they may unconsciously "roleplay" these tropes because that is the pattern found in their training data.
Concerning.
__________________
Ekco - 60 Wiz // Oshieh - 60 Dru // Tpow - 60 Nec // Kusanagi - 54 Pal // Losthawk - 52 Rng // Tiltuesday - EC mule
Reply With Quote