anzumitsu
Joined 1 year ago
Karma
18
Submissions
9
Member since
Apr 28
Joined 1 year ago
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.
I do get where you’re coming from though. I wish these systems had been trained to be clearly robotic and unfeeling.