On the other hand I find it quite disturbing to see people be unpleasant or even downright cruel to something that, on a surface level, interacts with you like it’s a thinking, feeling being. Surely you should feel some aversion towards doing so?
I do get where you’re coming from though. I wish these systems had been trained to be clearly robotic and unfeeling.
To play devils advocate, isn’t any security approach fundamentally statistical because we exist in the real world, not the abstract world of security models, programming language specifications, and abstract machines? There’s always going to be a chance of a compiler bug, a runtime error, a programmer error, a security flaw in a processor, whatever.
Now, personally I’d still rather take the approach that at least attempts to get that probability to zero through deterministic methods than leave it up to model alignment. But it’s also not completely unthinkable to me that we eventually reach a place where the probability of a misaligned model is sufficiently low to be comparable to the probability of an error occurring in your security model.
Can you give some examples of your 100 daily actions? I’m struggling to understand how you’re scheduling so many things, like I’m sure I complete 100 actions in a day but most are going to be things like “brush my teeth” or “clean up the dinner dishes”, which I personally wouldn’t schedule.
I do get where you’re coming from though. I wish these systems had been trained to be clearly robotic and unfeeling.