In you're in favor of "AI safety" (broad definition), what's your most compelling cast-length argument?

We don’t know what perverse path it might take to maximize its objective function, nor do we have a handle on how to craft its objective function to balance beneficence, human autonomy, and non-maleficence. We sort of see this with recommendation algos already.

Design and software at Apple. Also into AI, philosophy of mind, ethics.

also happen to think our proximity to AGI is overstated, so it’s kind of moot