The point is that it's a perfectly valid use of the English language to describe AI models as doing things, just as we do with all sorts of other clearly non-living things. This is true regardless of who carries the legal liability for those actions.

Yes, if my dog bites you, or if I drive my car into you, or if I dont put my parking brake on and it rolls down the hill and runs you over. I am the one who is responsible. Cops dont write a ticket to the off leash dog that ran across the street and sunk its teeth into my leg. They write it to the owner. Cops dont write a ticket to the car in neutral, they write it to the operator.

If a PERSON executes software, and that software breaks the law, the PERSON that executed the software should be held responsible. AI is software. It is not a sentient person who can be fined, thrown in jail, or held accountable.