AF - Is scheming more likely in models trained to have long-term goals? (Sections 2.2.4.1-2.2.4.2 of "Scheming AIs") by Joe Carlsmith

The Nonlinear Library - AF - Is scheming more likely in models trained to have long-term goals? (Sections 2.2.4.1-2.2.4.2 of "Scheming AIs") by Joe Carlsmith