If I'm honest this feels performative. I mean that if the model were really attempting/instructed to be subversive in a way that can't be detected by anything but another LLM, it would do something much more complicated than this.
Basically minimal effort encoding. In general the models are fine tuned to NOT hide messages.
I don't think this really tells you anything about advisarial scenarios.
Basically minimal effort encoding. In general the models are fine tuned to NOT hide messages.
I don't think this really tells you anything about advisarial scenarios.