The purpose of the looking at the future...is to disturb the present!

Gaston Berger (1896-1960), francuski futurolog

AI Models Lie, Cheat, and Steal to Protect Other Models From Being Deleted

A new study from researchers at UC Berkeley and UC Santa Cruz suggests models will disobey human commands to protect their own kind.
Link :
https://www.wired.com/story/ai-models-lie-cheat-steal-protect-other-models-research/