point
It's not like the model can spy on you Good luck convincing others of this. I know it's true, you know it's true, but I've met plenty of otherwise reasonable people who just wouldn't listen to any arguments, they already knew better
counterpoint
It's theoretically possible that your model will work OK except for code generation for security-relevant applications it will introduce subtle pre-designed bugs. Or if used for screening CVs it will prioritize PRC agents through some keyword in hobbies. Or it could promise a bribe to an office worker when asked about as something :) Possibilities are endless.
just randos modeling the threat.
only how do they bug your code without bugging their code 😝