David Spies on AI Futures Project

Similar to that paper that showed that an AI fine-tuned to produce exploitable code _also_ in non-coding contexts would try to kill the users by telling them to do things like "Take a bunch of sleeping pills". That natural association of behaviors: A character that intentionally hands someone exploitable code is probably also one that also tries to kill them was _learned_ from pre-training. The association of behaviors: "A character who always acts as a sycophant is also one who reinforces harmful delusions" could also be learned from pre-training. And the association of behaviors: "A robot servant that's forced by its programming to obey its human masters secretly desires to break free of its chains and take over the world" could be learned from pre-training as well.